SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.04579 · NeurIPS · 2022

Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs

Michael Bronstein, Pietro Liò, Cristian Bodnar, Francesco Di, Benjamin Chamberlain Twitter

arXiv · PDF · Open in the Atlas

Code that ran

None of the 1 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (1 no recorded run), measured 2026-11-21; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2202.04579.json · badge: /api/ran/2202.04579.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
twitter-research/neural-sheaf-diffusion canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
SheafDiffusion Not yet run
unverified (harvested, no recorded run)
twitter-research/neural-sheaf-diffusion/models/sheaf_base.py
code served (permissive licence) · get_code("2000cda4ded21558")
How it ran

no invocation recorded.

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Cellular sheaves equip graphs with a "geometrical" structure by assigning vector spaces and linear maps to nodes and edges. Graph Neural Networks (GNNs) implicitly assume a graph with a trivial underlying sheaf. This choice is reflected in the structure of the graph Laplacian operator, the properties of the associated diffusion equation, and the characteristics of the convolutional models that discretise this equation. In this paper, we use cellular sheaf theory to show that the underlying geometry of the graph is deeply linked with the performance of GNNs in heterophilic settings and their oversmoothing behaviour. By considering a hierarchy of increasingly general sheaves, we study how the ability of the sheaf diffusion process to achieve linear separation of the classes in the infinite time limit expands. At the same time, we prove that when the sheaf is non-trivial, discretised parametric diffusion processes have greater control than GNNs over their asymptotic behaviour. On the practical side, we study how sheaves can be learned from data. The resulting sheaf diffusion models have many desirable properties that address the limitations of classical graph diffusion equations (and corresponding GNN models) and obtain competitive results in heterophilic settings. Overall, our work provides new connections between GNNs and algebraic topology and would be of interest to both fields. * Work done as a research intern at Twitter. † Proved the results in Section 3.1. Our code is available at https://github.com/twitter-research/neural-sheaf-diffusion. 36th Conference on Neural Information Processing Systems (NeurIPS 2022).

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2202.04579")
get_code_for_paper("2202.04579")
have("2202.04579")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2202.04579.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2202.04579.svg)](https://syntology.ai/paper/2202.04579)

Connect an agent — have() is free.