betaFeedback

WorksComputer Science

Topological Deep Learning Challenge 2026: Bridging the Gap

Abstract

This paper describes the 2026 edition of the Topological Deep Learning Challenge: Bridging the Gap, hosted at the second Topology, Algebra, and Geometry in Data Science (TAG-DS) Conference. Where previous editions grew the modelling and data ecosystem of Topological Deep Learning (TDL), this edition set out to place Graph Neural Networks (GNNs) and Topological Neural Networks (TNNs) side by side under a single evaluation pipeline. Participants implemented recent state-of-the-art architectures in TopoBench, with Track 1 covering GNNs and Track 2 covering TNNs. They evaluated these implementations on shared synthetic benchmarks generated with GraphUniverse, which independently controls homophily, average degree and degree-distribution heaviness. The challenge yielded 68 qualifying submissions from 34 teams, spanning the graph, simplicial, cellular, hypergraph and combinatorial domains. For the first time, submissions were also tracked on a public leaderboard, which we summarize and analyze here. Our analysis finds that the differences between the submitted tracks are strongly task-dependent: the mean accuracy gap is modest on community detection, while on triangle counting the Track 1 mean error is 1.85 times the Track 2 mean. Several structurally informed GNNs also outperform the Track 2 mean on triangle counting.

Main organizers, equal contribution. Corresponding email: [email protected]

Introduction

Many physical systems, from molecules to galaxies, are driven by interactions among their components: chemical interactions between atoms, functional connectivity between brain regions, or gravitational forces between stars. Conventionally, these relations are modeled with graphs, allowing Graph Neural Networks (GNNs) (Scarselli et al., 2008) to extract key insights (Kipf and Welling, 2017). However, these systems also involve richer interactions that extend beyond the pairwise relations graphs encode. Topological Neural Networks (TNNs) have emerged to address this limitation by accounting for higher-order interactions (Hajij et al., 2022; Bodnar, 2022; Papillon et al., 2023b), extending message passing to simplicial, cellular, hypergraph and combinatorial domains using concepts from algebraic topology [10, 3].

Despite this shared lineage, the GNN and Topological Deep Learning (TDL) communities have largely operated in parallel. The two fields are often presented as distinct paradigms, yet they are deeply intertwined, and a growing body of work studies the interplay between standard message passing and higher-order representations. Comparisons between GNNs and TNNs remain difficult because published results typically use different codebases, datasets, tasks, and tuning budgets. This leaves a central empirical question: when does higher-order structure improve performance?

Building on the three previous editions of the challenge (Papillon et al., 2023a; Bernárdez et al., 2024; Bernárdez et al., 2026), the Topological Deep Learning Challenge 2026 set the stage for closing this gap. Participants were asked to implement recent state-of-the-art architectures from either literature into TopoBench (Telyatnikov et al., 2025), the open-source platform for developing and benchmarking TDL models, and to evaluate them through a single shared pipeline on synthetic graphs generated with GraphUniverse (Van Langendonck et al., 2026). Because GraphUniverse generates graphs with prescribed structural properties, the resulting benchmark allows us to examine how each architecture responds to changes in homophily, average degree and degree-distribution heaviness under a controlled generative design.

The challenge concluded with 68 valid submissions from 34 teams, submitted by 45 registered participants. Thirty-seven submissions implemented graph architectures in Track 1; thirty-one implemented higher-order architectures in Track 2, distributed across the simplicial, cellular, hypergraph and combinatorial domains. For the first time in the history of the challenge, submissions were additionally evaluated on a common benchmark suite and tracked on a public leaderboard. This paper details the challenge setup and submission requirements, lists all submissions and winners, and presents an analysis of the leaderboard results.

Setup of the Challenge

The challenge1 was hosted at the second Topology, Algebra, and Geometry in Data Science (TAG-DS) Conference and sponsored by Arlequin AI and New Theory. Participants were asked to implement a recent state-of-the-art message-passing model into TopoBench in one of two tracks:

  • Track 1 — Graph Neural Networks (GNNs). Architectures operating on graph structures, including message-passing networks and graph transformers with structural encodings.

  • Track 2 — Topological Neural Networks (TNNs). Higher-order message-passing models leveraging rich topological domains, namely simplicial, cellular, hypergraph and combinatorial complexes.

While the tracks were judged separately, the cross-track analysis uses a common evaluation protocol and controlled dataset family.

Guidelines

Participation was free and open to everyone. To enroll, participants had to open a Pull Request (PR) on TopoBench, fill out the Registration Google Form with PR and team information, and tag the PR with the appropriate track label (track-1-gnn or track-2-tnn). Teams were accepted with a maximum of two members, though larger teams were possible upon approval. A single team was permitted to submit multiple PRs, both within and across tracks. The final submission deadline was August 1st, 2026 (AoE).

Submissions were required to implement models already proposed in the literature and to cite the associated publication or pre-print in the PR description. Each PR could contain at most one core model architecture; models with several significant variants were asked to supply a separate configuration file per variant. Participants were encouraged to submit early, both to leave time to resolve integration issues and because, where multiple high-quality submissions covered the same architecture, earlier submissions were given priority.

Consistent with the aims of an open environment for sharing participation, this activity was completely voluntary. However, due to legal restrictions, individuals affiliated with institutions on the Restricted Foreign Research Institutions list were not eligible for reward outcomes, including co-authorship on this white paper.

Submission Requirements

A submission consisted of a Pull Request to TopoBench repository, titled following the format Track: [Track1|Track2]; Team Name: <team name>; Model: <model name>. To be valid, the PR had to pass all integration tests, including linting and formatting. Three components were required of every submission, across tracks:

  1. Backbone. The model implemented as a torch.nn.Module and placed in topobench/nn/backbones/{domain}/{model_name}.py, where {domain} is one of graph, simplicial, cell, hypergraph, combinatorial or non-relational.

  2. Hydra configuration. A YAML file at configs/model/{domain}/{model_name}.yaml specifying the full TBModel composition: feature encoder, backbone, backbone wrapper and readout.

  1. Results file. The results.json produced by running the provided evaluation notebook, TopoBench/2026_tdl_challenge/run_evaluation.ipynb, on the submitted model. This file records the model’s performance on the benchmark tasks and available resource measurements, and is what feeds the public leaderboard.

Beyond the backbone, participants were encouraged to exploit TopoBench’s modular architecture by contributing custom feature encoders, readouts, backbone wrappers or losses where their chosen model required them, each inheriting from the corresponding abstract base class and discovered automatically by the framework. This was a deliberate design choice: it enriches the ecosystem with reusable components rather than with monolithic model files.

Testing. All contributed files had to pass the pre-existing unit tests, and any method or class not already covered had to be accompanied by new tests mirroring the source directory structure. Coverage, measured with Codecov, had to match or exceed 93%. Each submission also had to fill in test/pipeline/test_pipeline.py to demonstrate that the full training pipeline runs end-to-end, and the evaluation notebook had to run successfully with the submitted model.

Evaluation Method

To decide the winners in each track, a panel of TopoBench maintainers and collaborators voted on their preferred submissions, and the Condorcet method was used to produce a ranking. Reviewers were asked to base their rankings on the following criteria, which were visible to participants throughout:

  • Correctness: Does the submission correctly implement the model as described in the literature? Modifications required to respect TopoBench’s computational constraints were permitted.

  • Code quality: How readable and clean is the implementation? How well does the submission respect the requirements, including unit tests and memory usage?

  • Benchmark on GraphUniverse datasets: Is the model correctly benchmarked on the provided datasets? Does it produce reasonable results?

  • Documentation & tests: Do docstrings clearly describe the code, and do they make explicit reference to the original equations in the associated paper and/or the original implementation? Are unit tests robust?

The award criteria assess the quality and reusability of model implementations, not their final benchmark performance. No minimum training performance was required, and the highest leaderboard score did not determine the winner. The leaderboard supports the comparative analysis in § 5.

For the first time, reviewers were permitted to use AI tools to help manage the volume of submissions. In Track 1, an AI reviewer agent was given the same instructions as the human reviewers. It graded each submission against the rubric and flagged the bottom tier of submissions. Track 1 reviewers could use these flags at their discretion. Reviewers were asked to disclose their use of AI in their responses.

Prizes

With thanks to our sponsors, this edition offered cash prizes of $1,000 USD for first place and $400 USD for second place in each track, with Track 1 sponsored by New Theory and Track 2 by Arlequin AI. This year, honorable mentions also carried cash prizes, with $700 USD split across outstanding submissions. In addition, selected teams were invited for research internships at the Geometric Intelligence Lab (University of California, Santa Barbara) and the Intelligent Maintenance and Operations Systems (IMOS) Lab (École Polytechnique Fédérale de Lausanne, Switzerland).

Software Practices

All submitted code had to comply with the challenge’s GitHub Action workflow, passing all tests, linting and formatting checks. To ensure consistency, participants working in the simplicial, cellular or combinatorial domains were asked to use TopoNetX’s (Hajij et al., 2024) classes to manage the corresponding complexes.

Benchmarking Protocol

The defining novelty of this edition is the use of a shared evaluation pipeline and dataset family for the cross-track comparison. This section describes that protocol.

Controlled Synthetic Data

Evaluation datasets were generated with GraphUniverse (Van Langendonck et al., 2026), a framework for sampling synthetic graphs with prescribed structural properties. Three structural axes were varied independently:

  • Homophily, at three levels: low (0–0.1), mid (0.4–0.6) and high (0.9–1.0).

  • Average degree, at two levels: low (1–2.5) and high (4–5).

  • Power-law exponent γ\gamma of the degree distribution, at two levels: low (1.5–2, heavy-tailed) and high (4–5, homogeneous).

The full grid therefore contains 3×2×2=123 \times2 \times2 = 12 configurations. The prescribed evaluation uses three training seeds per configuration, totaling 36 runs per task and 72 per model variant. This controlled design allows us to examine how model performance changes across prescribed structural regimes.

Tasks and Metrics

We consider two tasks, probing community structure and local substructure:

  • Community detection, a node-classification task scored by accuracy (higher is better). This task is well aligned with the inductive bias of standard message passing: it rewards models that aggregate and smooth information over neighbourhoods.

  • Triangle counting, a regression task scored by MSEtest/∑G∈Dtestτ(G)\mathrm{MSE}_{\mathrm{test}}/\sum_{G\in D_{\mathrm{test}}}\tau(G) (lower is better), where τ(G)\tau(G) counts triangles in each test graph’s undirected edge structure after preprocessing. Counting triangles is provably beyond the reach of 1-WL-bounded message-passing networks.

Leaderboard

Results were published on a public leaderboard2. For each structural setting, scores are reported as the mean ±\pm standard deviation of the in-distribution test metric across three training seeds; summaries across settings include up to 36 runs per task. The analysis uses the submitted result reports, with one variant per PR selected as described in § 5.

Two caveats underscore these results. First, the scores describe the implementations and configurations submitted by participants rather than the best achievable performance of each method. Second, implementations were contributed by different participants with differing familiarity with the underlying papers. While the review process checked for correctness as part of the rubric, residual implementation variance potentially impacts leaderboard performance.

Submissions and Winners

The challenge received 68 valid submissions from 34 teams, submitted by 45 registered participants. Participation was close to evenly split between the two tracks: 37 submissions in Track 1 and 31 in Track 2. Within Track 2, submissions covered all four higher-order domains supported by TopoBench: ten simplicial, six cellular, seven hypergraph and eight combinatorial. Table 1 lists all submitted models, grouped by track and domain, with references to the underlying methods and links to their implementations. Additionally, Table 4 in Appendix A lists the co-authors belonging to each team, as well as the awards each team received.

Track 1 — GNNs
Graph37 submissions
ModelPR
AdvDIFFormer (Wu et al., 2025)399
BuNN ([2])319
CoGNN (Finkelshtein et al., 2024)369
Conn-NSD ([4])327
DNSD ([16])375
DSNN (Fiorini et al., 2026)412
ESC-GNN (Yan et al., 2024)419
FAGCN ([11])382
FAGCN ([11])388
FiGURe (Ekbote et al., 2023)360
GAMMA (Ghazizadeh et al., 2025)411
GATE (Mustafa and Burkholz, 2024)355
GAUGE (Sun et al., 2026)396
GFT (Wang et al., 2024)334
GPR-GNN (Chien et al., 2021)352
GREAD (Choi et al., 2023)415
GREAD (Choi et al., 2023)420
GRIT (Ma et al., 2023)370
GSN (Bouritsas et al., 2023)407
HeroFilter (Zhang et al., 2025a)384
HiD-Net (Li et al., 2024)335
HOD-GNN (Eitan et al., 2026)402
HyMN (Southern et al., 2025)421
ISN (Hernandez Caralt et al., 2026)374
JacobiConv (Wang and Zhang, 2022)383
LINKX (Lim et al., 2021)361
MTGCN (Pei et al., 2024)400
NSD ([15])332
NSP (Suk et al., 2022)326
NSP + Holonomy (Suk et al., 2022)373
OGFormer (Zhang et al., 2025b)378
PolyFilter GNN (Favard) (Guo and Wei, 2023)354
Polynormer (Deng et al., 2024)345
r-lMPNN (Paolino et al., 2024)404
SGFormer (Wu et al., 2023)359
SheafAN ([5])322
TopoPolynormer (Deng et al., 2024)353
Track 2 — TNNs
Simplicial10 submissions
ModelPR
Bi-SCNN (Yan and Kuruoglu, 2025)387
COSIMO (Einizade et al., 2025)392
CTNN (Hajij et al., 2025)405
Dir-SNN (Lecha et al., 2025)328
DirSNN (memory-safe, harmonic-aware) (Lecha et al., 2025)350
GSAN ([6])365
HiGCN (Huang et al., 2024)364
MPSN ([14])376
MPSN ([14])393
PolynomialFilterTNN (SNN) (Ebli et al., 2020)414
Cellular6 submissions
AirTNN (Fiorellino et al., 2024)329
AirTNN (Fiorellino et al., 2024)394
Cellular Transformer ([1])371
CIN ([13])363
DiffLift-SMCN (Franco et al., 2026; Eitan et al., 2025)406
SheafTSP (Tandon et al., 2026)410
Hypergraph7 submissions
DPHGNN (Saxena et al., 2024)398
DSHN (Mule et al., 2026)408
EHNN (Kim et al., 2022)366
HyperGCN (Yadati et al., 2019)413
PhenomNN (Wang et al., 2023)367
SheafHyperGNN (Duta et al., 2023)321
WHNN (Duta and Liò, 2025)417
Combinatorial8 submissions
CTNN (copresheaf, gated) (Hajij et al., 2025)418
ETNN ([7])320
ETNN-CoordinatePolicy (structural-LapPE) ([7])391
ETNN-LapPE ([7])362
HMC (Hajij et al., 2022)416
SMCN (Eitan et al., 2025)397
TopNets (Verma et al., 2024)333
TopoU-Net (Gaurav et al., 2026)372

Table 1. All 68 submissions, grouped by track and domain, with models ordered alphabetically within each domain. Citations identify the underlying methods, and PR numbers link to each implementation. Repeated models denote separate submissions. Appendix A lists teams; Appendix B reports scores for the 65 entries in the comparative analysis.

TeamCo-authorsTrackPR numbersAward
AdamGohainAdam GohainT1359
CoPreSheafersChristine Zeh, Lennart BastianT2418
CtrlAltMeSalwa KhattamiT2397
DeveshKaushalDevesh KaushalT2392
E(n)igmaGaurav KhanalT2320, 362, 391T2 joint 1st (ETNN-CoordinatePolicy)
Fernando EspinosaFernando David Espinosa IñiguezT2410
Francesco OrsiFrancesco OrsiT2393, 394
GiggioIlGriggioAlessio CompariniT2376
GroldGrold Otieno MboyaT2350
howyadoinDario Loi, Gabriele OnoratoT1+T2322, 326, 405, 408, 412T1 1st (DSNN); HM portfolio
KajolyaKolya Lettl, Kajal SinglaT1407
kxdenzKaden ZhengT1419
LangDiffJonas MüllerT1335, 399, 400, 420
LettliniKolya Lettl, Ghazal MostofiT1396
LoopCounterSud AthreyaT2364, 365, 366, 367
MISN_AYMohammad Yusuf, Ankit KumarT1+T2382, 383, 387, 388
One Ring to Lift Them AllJorge Luiz FrancoT2406HM differentiable liftings
Oversmooth operatorsGabriel Franco, Yelizaveta FalkouskayaT1+T2398, 404
Perelyn ResearchMichael Banf, Dominik FilipiakT1361
Prasanna28DevadigaPrasanna DevadigaT1327
PushparajDPushparaj DevadigaT1352, 355
r2Anier Velasco SotomayorT1+T2329, 354, 360, 414
Raj PatilRaj PatilT1411
rayquazaLuigi Petti, Eric Dolores-CuencaT2413
RemyStefano BlandoT2417
s/pairwise/hoValentina SánchezT2321
SheafuAnkit Grover, Rémi BourgerieT1373, 374, 375HM supplementary analysis
SweetLessonAarav Gupta, Riyan PatelT1345, 353, 402T1 joint 2nd (HOD-GNN)
TJPaikTaejin PaikT1+T2328, 332, 333, 334
TopoCoopMarcos Chávez Mesa, Gabriel Chaviano DíazT1+T2369, 371
topolabChenguang XuT1+T2415, 416
TripleAAmirreza Akbari, Alireza MohammadianT1+T2363, 370, 372, 378, 384T1 joint 2nd (GRIT); T2 joint 1st (TopoU-Net); HM portfolio
weeyevVihan TiwariT1421
yeahkitoryHisataka KajitaT1319

Table 4. Teams and their co-authors, in alphabetical order of team name. T1 and T2 denote Track 1 (GNN) and Track 2 (TNN); HM denotes an honorable mention (§ 4). A dash marks a team for which no author information was provided.

Winners and Honorable Mentions

The winners were announced publicly at the second TAG-DS Conference, on social media, and on the official challenge website. We emphasize that regardless of final rankings, the organizers and reviewers were impressed by the quality of the submissions and their contribution to the TopoBench ecosystem. We warmly congratulate all participants.

Track 1 — Graph Neural Networks.

  • First place ($1,000): DSNN, Team howyadoin (Dario Loi and Gabriele Onorato; PR #412).

  • Joint second place ($200 each): GRIT, Team TripleA (Amirreza Akbari and Alireza Mohammadian; PR #370), and HOD-GNN, Team SweetLesson (Aarav Gupta and Riyan Patel; PR #402).

Track 2 — Topological Neural Networks. The Condorcet evaluation resulted in a tie, and the Track 2 prize was divided equally between the two co-winners:

  • Joint first place ($700 each): ETNN-CoordinatePolicy, Team E(n)igma (Gaurav Khanal; PR #391), and TopoU-Net, Team TripleA (Amirreza Akbari and Alireza Mohammadian; PR #372).

Honorable mentions.

  • Excellent portfolio ($150 each): Teams howyadoin (Dario Loi and Gabriele Onorato) and TripleA (Amirreza Akbari and Alireza Mohammadian), recognised for multiple high-quality contributions across both tracks.

  • Novel infrastructure with differentiable liftings ($200): DiffLift-SMCN, Team One Ring to Lift Them All (Jorge Luiz Franco; PR #406).

  • Outstanding supplementary analysis ($200): Neural Sheaf Propagation + Holonomy Measurement, Team Sheafu (Ankit Grover and Rémi Bourgerie; PR #373 with a companion paper Grover and Bourgerie (2026)).

Leaderboard Results and Analysis

This section presents the first cross-track comparison in the history of the challenge. We include 65 entries3: 34 in Track 1 and 31 in Track 2. For each PR, we consider variants of the submitted model with complete benchmark results, select the variant with the highest mean in-distribution community-detection accuracy over the full evaluation grid, and use that same variant for both tasks4. For each task, we first average the three seed scores within each setting, then average the 12 setting means to obtain one score per PR. Track and domain means give each PR equal weight. Table 2 reports the per-track aggregates, and Table 3 breaks them down by topological domain. Complete leaderboards for both tasks are given in Appendix B.

TracknnAllLowMidHighLowHigh
Community detection — accuracy (↑\uparrow)
Track 1 (GNN)340.42410.30880.38690.57650.39910.4491
Track 2 (TNN)310.43430.30610.40000.59700.40990.4588
Triangle counting — MSE per triangle (↓\downarrow)
Track 1 (GNN)340.70970.08870.60991.43040.35791.0614
Track 2 (TNN)310.38280.04280.32510.78050.18580.5798

Table 2. Mean in-distribution test score per track, averaged over submissions in the 65-entry analysis cohort (§ 5). Columns marginalise the GraphUniverse configuration grid over homophily and average degree. PRs #319, #327 and #382 are excluded.

DomainnnCommunity detection (↑\uparrow) Allhloh_{lo}hmidh_{mid}hhih_{hi}Triangle counting (↓\downarrow) Allhloh_{lo}hmidh_{mid}hhih_{hi}
Graph (T1)340.42410.30880.38690.57650.70970.08870.60991.4304
Simplicial100.44110.31410.40300.60620.25860.01190.21840.5455
Cell60.43560.28460.39940.62270.31440.04670.26520.6314
Hypergraph70.44510.31960.40670.60900.65050.08670.52531.3393
Combinatorial80.41550.30040.39070.55550.35510.04030.32810.6970

Table 3. Mean in-distribution test score per topological domain, broken down by homophily regime. Track 1 submissions all operate on the graph domain. The 65-entry analysis cohort is defined in § 5.

Performance Differences Across Tasks

The clearest takeaway from these results is that the mean performance advantage of TNNs over GNNs is task-dependent. For example, it is modest on community detection and more pronounced on triangle counting.

On community detection, Track 2 attains a mean accuracy of 0.4343 against 0.4241 for Track 1, a modest descriptive difference of 1.02 percentage points. The best individual result comes from Track 1: GRIT (PR #370) reaches 0.5207, ahead of the best Track 2 model, HiGCN (PR #364), at 0.4869.

On triangle counting, the picture changes sharply. Track 2 attains a mean error of 0.3828 against 0.7097 for Track 1; the Track 1 mean is 1.85 times the Track 2 mean. The best submission overall is a combinatorial model, CTNN (PR #418), at 0.0024—more than two orders of magnitude below the Track 1 mean. This is consistent with the motivation behind encoding higher-order structure. We note that the track comparison does not isolate the contribution of that structure from other architectural and implementation choices.

Table 3 gives a more detailed view. On triangle counting, simplicial submissions have the lowest mean error (0.2586), followed by cellular (0.3144), combinatorial (0.3551), hypergraph (0.6505) and graph submissions (0.7097).

Structural Information Beyond Track Labels

Going beyond track aggregations, we find that several of the strongest triangle-counting submissions are Track 1 models. For example, TopoPolynormer (PR #353, 0.0451), ESC-GNN (PR #419, 0.0552), GSN (PR #407, 0.0665), GRIT (PR #370, 0.0693) and HOD-GNN (PR #402, 0.0802) all outperform the Track 2 mean, and several outperform the majority of Track 2 submissions. A common property of these architectures is that while they operate on graph-based domains, they inject substructure or structural-encoding information, such as subgraph counts, random-walk encodings, or explicit higher-order descriptors.

These results show that a graph-domain model equipped with structural information can perform competitively on triangle counting. Higher-order domains offer another way to supply structural information, but performance also varies substantially among TNN submissions. Establishing the separate contributions of the lifting, structural encoding and message-passing scheme via controlled ablations is a promising avenue for future work.

Structural Sensitivity

The controlled grid allows us to ask how each family responds to the structural axes. Figure 1 reveals substantial overlap between GNNs and TNNs on community detection. At high homophily, their median accuracies are close (0.6170 and 0.6161, respectively), despite the larger difference between their means. On triangle counting, TNNs achieve lower median error across all three homophily regimes, showing that their advantage is also reflected in the medians. Nevertheless, performance varies considerably within each family, and several GNN submissions achieve errors below the TNN median in every homophily regime.

Submission-score distributions by homophily

Figure 1. Submission-score distributions by homophily, complementing Table 2. Each dot is one submission’s mean over four degree–power-law settings and three seeds per setting (34 GNNs; 31 TNNs). Boxes span the interquartile range, with a line marking the median. Whiskers extend to the most extreme observations within 1.5 interquartile ranges below the first quartile or above the third quartile. Diamonds mark arithmetic track means. Axes are shared within each task; triangle-counting error is shown on a logarithmic scale.

Homophily. On community detection, both tracks lose accuracy as homophily drops: from 0.5765 to 0.3088 for Track 1 and from 0.5970 to 0.3061 for Track 2. The Track 2 mean exceeds the Track 1 mean by 2.04 percentage points at high homophily and 1.31 at mid homophily, while Track 1 leads by 0.28 percentage points at low homophily. Thus, the observed Track 2 advantage does not extend to the low-homophily regime on this task. On triangle counting, the direction is reversed: mean error decreases as homophily falls, from 1.4304 to 0.0887 for Track 1 and from 0.7805 to 0.0428 for Track 2.

Average degree and degree distribution. Both tracks perform better on community detection at high average degree than at low (0.4491 versus 0.3991 for Track 1; 0.4588 versus 0.4099 for Track 2), consistent with denser neighborhoods carrying more signal. On triangle counting the pattern inverts, with normalized error rising at high degree and at high homophily in both tracks. Heavy-tailed degree distributions (low γ\gamma) also yield higher mean normalized error than homogeneous ones in both tracks.

Leaderboard Position and Award Outcome

Because both a leaderboard and a set of awards appear in this paper for the first time, we make their relationship explicit. As described in § 2.3, awards were decided by Condorcet vote on implementation quality, not on benchmark score, and the two rankings differ considerably: the Track 1 winner, DSNN (PR #412), ranks 62nd of 65 on community detection, and the Track 2 co-winner TopoU-Net (PR #372) ranks 59th. The awards recognize implementation quality and reusability; Table 5 and Table 6 describe performance on the two benchmark tasks. Award outcomes and leaderboard positions should therefore be interpreted separately.

#ModelTrackTeamScore ↑\uparrow
1Graph Inductive Bias Transformer (GRIT)T1 · GNNTripleA0.5207
2Filter Bank GNN (FiGURe)T1 · GNNr20.4986
3PolyFilter GNN (Favard)T1 · GNNr20.4977
4HiGCNT2 · TNNLoopCounter0.4869
5GREADT1 · GNNtopolab0.4816
6TopoPolynormerT1 · GNNSweetLesson0.4798
7Deep Neural Sheaf Diffusion (DNSD)T1 · GNNSheafu0.4743
8ESC-GNNT1 · GNNkxdenz0.4743
9MPSNT2 · TNNGiggioIlGriggio0.4742
10SheafTSPT2 · TNNFernando Espinosa0.4735
11SheafHyperGNNT2 · TNNs/pairwise/ho0.4728
12DiffLift-SMCNT2 · TNNOne Ring to Lift Them All0.4719
13Generalized PageRank GNNT1 · GNNPushparajD0.4697
14MTGCNT1 · GNNLangDiff0.4697
15CTNN (copresheaf, gated)T2 · TNNCoPreSheafers0.4690
16HiD-NetT1 · GNNLangDiff0.4685
17Cell Isomorphism Network (CIN)T2 · TNNTripleA0.4681
18JacobiConvT1 · GNNMISN AY0.4649
19r−ℓr-\ellMPNNT1 · GNNOversmooth operators0.4648
20DPHGNNT2 · TNNOversmooth operators0.4641
21DSHNT2 · TNNhowyadoin0.4633
22HMCT2 · TNNtopolab0.4596
23CoGNNT1 · GNNTopoCoop0.4585
24HeroFilterT1 · GNNTripleA0.4574
25OGFormerT1 · GNNTripleA0.4574
26EHNNT2 · TNNLoopCounter0.4566
27CTNNT2 · TNNhowyadoin0.4561
28GSANT2 · TNNLoopCounter0.4556
29PolynormerT1 · GNNSweetLesson0.4550
30ETNN-LapPET2 · TNNE(n)igma0.4545
31ETNN-CoordinatePolicy (structural-LapPE)T2 · TNNE(n)igma0.4543
32ETNNT2 · TNNE(n)igma0.4534
33GATET1 · GNNPushparajD0.4457
34GFTT1 · GNNTJPaik0.4451
35WHNNT2 · TNNRemy0.4435
36DirSNN (Memory-Safe, Harmonic-Aware)T2 · TNNGrold0.4414
37HyMNT1 · GNNweeyev0.4408
38Cellular TransformerT2 · TNNTopoCoop0.4400
39HOD-GNNT1 · GNNSweetLesson0.4395
40MPSNT2 · TNNFrancesco Orsi0.4387
41SGFormerT1 · GNNAdamGohain0.4375
42PolynomialFilterTNN (SNN)T2 · TNNr20.4368
43COSIMOT2 · TNNDeveshKaushal0.4333
#ModelTrackTeamScore ↑\uparrow
44PhenomNNT2 · TNNLoopCounter0.4308
45GAMMAT1 · GNNRaj Patil0.4257
46GAUGE (Riemannian Graph Foundation Model)T1 · GNNLettlini0.4219
47Neural Sheaf Diffusion (NSD)T1 · GNNTJPaik0.4113
48Bi-SCNNT2 · TNNMISN_AY0.4057
49AdvDIFFormerT1 · GNNLangDiff0.4023
50AirTNNT2 · TNNFrancesco Orsi0.4007
51GREADT1 · GNNLangDiff0.3937
52SheafANT1 · GNNhowyadoin0.3887
53Neural Sheaf PropagationT1 · GNNhowyadoin0.3852
54HyperGCNT2 · TNNrayquaza0.3847
55Directed Simplicial Neural Networks (Dir-SNN)T2 · TNNTJPaik0.3821
56Neural Sheaf Propagation + Holonomy MeasurementT1 · GNNSheafu0.3817
57FAGCNT1 · GNNMISN_AY0.3813
58SMCNT2 · TNNCtrlAltMe0.3697
59TopoU-NetT2 · TNNTripleA0.3666
60LINKXT1 · GNNPerelyn Research0.3628
61AirTNNT2 · TNNr20.3594
62DSNNT1 · GNNhowyadoin0.3081
63TopNetsT2 · TNNTJPaik0.2970
64Identity Sheaf Network (ISN)T1 · GNNSheafu0.2755
65GSNT1 · GNNKajolya0.0795

Table 5. Community-detection leaderboard for the 65-entry analysis cohort (accuracy, higher is better; § 5). Ranks use full-precision means.

#ModelTrackTeamScore ↓
1CTNN (copresheaf, gated)T2 · TNNCoPreSheafers0.0024
2SheafTSPT2 · TNNFernando Espinosa0.0108
3MPSNT2 · TNNGiggioIlGriggio0.0287
4MPSNT2 · TNNFrancesco Orsi0.0333
5TopoPolynormerT1 · GNNSweetLesson0.0451
6COSIMOT2 · TNNDeveshKaushal0.0504
7ESC-GNNT1 · GNNkxdenz0.0552
8GSNT1 · GNNKajolya0.0665
9Graph Inductive Bias Transformer (GRIT)T1 · GNNTripleA0.0693
10HOD-GNNT1 · GNNSweetLesson0.0802
11ETNN-LapPET2 · TNNE(n)igma0.1147
12TopNetsT2 · TNNTJPaik0.1192
13DiffLift-SMCNT2 · TNNOne Ring to Lift Them All0.1201
14ETNN-CoordinatePolicy (structural-LapPE)T2 · TNNE(n)igma0.1211
15ETNNT2 · TNNE(n)igma0.1213
16rr-ℓ\ellMPNNT1 · GNNOversmooth operators0.1382
17HyMNT1 · GNNweeyev0.1497
18Bi-SCNNT2 · TNNMISN AY0.1498
19DirSNN (Memory-Safe, Harmonic-Aware)T2 · TNNGrold0.1543
20EHNNT2 · TNNLoopCounter0.1672
21Directed Simplicial Neural Networks (Dir-SNN)T2 · TNNTJPaik0.1716
22GSANT2 · TNNLoopCounter0.2570
23Cell Isomorphism Network (CIN)T2 · TNNTripleA0.2638
24DPHGNNT2 · TNNOversmooth operators0.4021
25PolynomialFilterTNN (SNN)T2 · TNNr20.4197
26AirTNNT2 · TNNFrancesco Orsi0.4538
27HMCT2 · TNNtopolab0.4843
28GFTT1 · GNNTJPaik0.4911
29Cellular TransformerT2 · TNNTopoCoop0.4982
30CTNNT2 · TNNhowyadoin0.5174
31Neural Sheaf Diffusion (NSD)T1 · GNNTJPaik0.5378
32AirTNNT2 · TNNr20.5401
33WHNNT2 · TNNRemy0.5492
34Identity Sheaf Network (ISN)T1 · GNNSheafu0.6044
35SheafHyperGNNT2 · TNNs/pairwise/ho0.6742
36HiGCNT2 · TNNLoopCounter0.8038
37SMCNT2 · TNNCtrlAltMe0.8219
38Neural Sheaf PropagationT1 · GNNhowyadoin0.8292
39Filter Bank GNN (FiGURe)T1 · GNNr20.8396
40PolyFilter GNN (Favard)T1 · GNNr20.8425
41Deep Neural Sheaf Diffusion (DNSD)T1 · GNNSheafu0.8658
42PolynormerT1 · GNNSweetLesson0.8721
43HiD-NetT1 · GNNLangDiff0.8753
44GAUGE (Riemannian Graph Foundation Model)T1 · GNNLettlini0.8758
45GREADT1 · GNNtopolab0.8773
46DSHNT2 · TNNhowyadoin0.9073
47DSNNT1 · GNNhowyadoin0.9099
48LINKXT1 · GNNPerelyn Research0.9132
#ModelTrackTeamScore ↓
49Neural Sheaf Propagation + Holonomy MeasurementT1 · GNNSheafu0.9158
50MTGCNT1 · GNNLangDiff0.9160
51GATET1 · GNNPushparajD0.9223
52PhenomNNT2 · TNNLoopCounter0.9243
53CoGNNT1 · GNNTopoCoop0.9286
54HyperGCNT2 · TNNrayquaza0.9289
55GAMMAT1 · GNNRaj Patil0.9301
56GREADT1 · GNNLangDiff0.9315
57Generalized PageRank GNNT1 · GNNPushparajD0.9325
58AdvDIFFormerT1 · GNNLangDiff0.9342
59SheafANT1 · GNNhowyadoin0.9345
60JacobiConvT1 · GNNMISN_AY0.9378
61HeroFilterT1 · GNNTripleA0.9470
62OGFormerT1 · GNNTripleA0.9509
63SGFormerT1 · GNNAdamGohain0.9658
64FAGCNT1 · GNNMISN_AY1.0438
65TopoU-NetT2 · TNNTripleA1.0560

Table 6. Triangle-counting leaderboard for the 65-entry analysis cohort (MSE per triangle, lower is better; § 5). Ranks use full-precision means.

Discussion & Concluding Remarks

This edition set out to answer two questions: how specific graph properties affect classical GNNs versus higher-order TNNs, and under what data regimes TNNs provide capabilities that standard GNNs do not. The results above provide a first, qualified answer to both.

On the first question, the community-detection gap narrows as homophily falls, with a small reversal in favour of GNNs at low homophily; a higher-order domain alone therefore does not establish robustness in that regime. On the second question, the submitted Track 2 cohort has lower mean error on triangle counting, while its mean accuracy advantage on community detection is small. The strong triangle-counting results of several Track 1 models suggest that both higher-order architectures and structurally informed graph models merit consideration for this task. Extending this observation to other motifs or tasks requires further evaluation.

We highlight the finding that substructure-aware GNNs close much of the gap on triangle counting as it points to a possible reframing of the comparison. Rather than a strict dichotomy between two model families, the results motivate studying the structural information supplied to models in both tracks. Both communities therefore face the same practical question: how to give networks access to structure beyond edges.

Several limitations bound these conclusions. The benchmark comprises two tasks on one family of synthetic graphs; performance on real-world data with correlated structural properties may differ. The results concern the submitted configurations, and their relative performance may change under different tuning budgets. Selecting variants by reported test accuracy can favour PRs with more variants and make community-detection performance estimates optimistic. Implementation quality, while reviewed, inevitably varies. Moreover, the aggregate statistics we report summarize a heterogeneous population of architectures, so track-level means should be interpreted as descriptions of the submissions rather than defined properties of the underlying model classes. Extending the benchmark suite with additional tasks and re-running it with per-model tuning are the natural next steps. Both are straightforward within TopoBench.

The challenge yielded 68 valid submissions from 34 teams, enriching TopoBench with implementations from both the GNN and TDL literatures. It also produced the first cross-track comparison in this challenge series under a shared benchmarking protocol, supported by a public leaderboard. We hope this infrastructure hosted in TopoBench will support research within the communities, facilitate comparisons between models, and encourage the exchange of methods and ideas between them.

Acknowledgments

We thank Arlequin AI and New Theory for sponsoring this edition of the challenge, the Geometric Intelligence Lab (UC Santa Barbara) and the IMOS Lab (EPFL) for supporting the internship opportunities, and the TAG-DS organizers for hosting the challenge. We are grateful to all TopoBench maintainers and collaborators who served on the review panel, and above all to the participants, whose contributions constitute the substance of this paper. N. M., G. B., and M. P. acknowledge partial support from NSF grant 2602079 and the Noyce foundation.

Teams and Co-authors

Table 4 associates each participating team with the individual co-authors of this paper who belong to it, and lists the pull requests and awards of each team. Participants who submitted under more than one team appear once per team.

Full Leaderboards

Tables 5 and 6 give the rankings of the 65 entries included in the comparative analysis, with variant selection and exclusions as described in § 5. Scores are means over the 12 GraphUniverse settings and three training seeds per setting; rankings use unrounded scores.

References

  1. [1]Rubén Ballester, Pablo Hernández-García, Mathilde Papillon, Claudio Battiloro, Nina Miolane, Tolga Birdal, Carles Casacuberta, Sergio Escalera, and Mustafa Hajji. Attending to Topological Spaces: The Cellular Transformer. arXiv preprint arXiv:2405.14094, 2024. URL https://arxiv.org/abs/2405.14094.
  2. [2]Jacob Bamberger, Federico Barbero, Xiaowen Dong, and Michael M. Bronstein. Bundle Neural Network for message diffusion on graphs. In International Conference on Learning Representations, 2025. URL https://openreview.net/forum?id=scI9307PLG.
  3. [3]Sergio Barbarossa and Stefania Sardellitti. Topological signal processing over simplicial complexes. IEEE Transactions on Signal Processing, 68:2992–3007, 2020.DOI
  4. [4]Federico Barbero, Cristian Bodnar, Haitz Sáez de Ocáriz Borde, Michael Bronstein, Petar Veličković, and Pietro Lió. Sheaf Neural Networks with Connection Laplacians. In Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022, volume 196 of Proceedings of Machine Learning Research, pages 28–36. PMLR, 2022a. URL https://proceedings.mlr.press/v196/barbero22a.html.arxiv.org/abs/2206.08702
  5. [5]Federico Barbero, Cristian Bodnar, Haitz Sáez de Ocáriz Borde, and Pietro Lió. Sheaf Attention Networks. NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations, 2022b. URL https://openreview.net/forum?id=LIDvgVjpkZr.
  6. [6]Claudio Battiloro, Lucia Testa, Lorenzo Giusti, Stefania Sardellitti, Paolo Di Lorenzo, and Sergio Barbarossa. Generalized Simplicial Attention Neural Networks. IEEE Transactions on Signal and Information Processing over Networks, 10:833–850, 2024. doi: 10.1109/TSIPN.2024.3485473. URL https://ieeexplore.ieee.org/document/10735150/.DOI
  7. [7]Claudio Battiloro, Ege Karaismailoğlu, Mauricio Tec, George Dasoulas, Michelle Audirac, and Francesca Dominici. E(n) Equivariant Topological Neural Networks. In International Conference on Learning Representations, 2025. URL https://openreview.net/forum?id=Ax3uIiEBVR.arxiv.org/abs/2405.15429
  8. [10]Christian Bick, Elizabeth Gross, Heather A Harrington, and Michael T Schaub. What are higher-order networks? SIAM Review, 65(3):686–731, 2023.DOI
  9. [11]Deyu Bo, Xiao Wang, Chuan Shi, and Huawei Shen. Beyond Low-frequency Information in Graph Convolutional Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 35(5):3950–3957, 2021. doi: 10.1609/aaai.v35i5.16514. URL https://ojs.aaai.org/index.php/AAAI/article/view/16514.DOI
  10. [13]Cristian Bodnar, Fabrizio Frasca, Nina Otter, Yuguang Wang, Pietro Liò, Guido F. Montúfar, and Michael Bronstein. Weisfeiler and Lehman Go Cellular: CW Networks. In Advances in Neural Information Processing Systems, volume 34, pages 2625–2640, 2021a. URL https://proceedings.neurips.cc/paper/2021/hash/157792e4abb490f99dbd738483e0d2d4-Abstract.html.
  11. [14]Cristian Bodnar, Fabrizio Frasca, Yuguang Wang, Nina Otter, Guido F. Montúfar, Pietro Liò, and Michael Bronstein. Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks. In Proceedings of the 38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Learning Research, pages 1026–1037. PMLR, 2021b. URL https://proceedings.mlr.press/v139/bodnar21a.html.
  12. [15]Cristian Bodnar, Francesco Di Giovanni, Benjamin Chamberlain, Pietro Liò, and Michael Bronstein. Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs. In Advances in Neural Information Processing Systems, volume 35, pages 18527–18541, 2022. doi: 10.52202/068431-1346. URL https://proceedings.neurips.cc/paper_files/paper/2022/hash/75c45fca2aa416ada062b26cc4fb7641-Abstract-Conference.html.DOI
  13. [16]Rémi Bourgerie, Sārūnas Girdzijauskas, and Viktoria Fodor. Deep Neural Sheaf Diffusion. arXiv preprint arXiv:2605.19021, 2026. URL https://arxiv.org/abs/2605.19021.

Paper details

Contents