SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.19285 · NeurIPS · 2023

Facilitating Graph Neural Networks with Random Walk on Simplicial Complexes

Muhan Zhang, Xiyuan Wang, Cai Zhou

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 4 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2310.19285.json · badge: /api/ran/2310.19285.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
zhouc20/HodgeRandomWalk canonical (classifier label)
classifier basis not recorded on the link
7 ran · 2 no recorded run
zhouc20/hodgerandomwalk canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
FunctionStatusWhere it lives
Delta_0 Ran
ran; our contract draft was wrong, not the code
zhouc20/hodgerandomwalk/graphgps/transform/hodge_decomposition.py
code served (permissive licence) · get_code("a59edb7a016ef8b4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (4, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Analyze the function:
# - alpha: used with .unsqueeze(0), .unsqueeze(1), and .repeat()
#   This suggests alpha is a 1D tensor
# - A: used with .shape[-1] to get last dimension, and multiplied with alpha
#   This suggests A is a 2D tensor
# - The operation: w_g = A * alpha.unsqueeze(0).repeat(A.shape[-1], 1) - A * alpha.unsqueeze(1).repeat(1, A.shape[-1])
#   alpha.unsqueeze(0) makes it (1, N), repeat(A.shape[-1], 1) makes it (A.shape[-1], N)
#   alpha.unsqueeze(1) makes it (N, 1), repeat(1, A.shape[-1]) makes it (N, A.shape[-1])
#   So A must be (A.shape[-1], A.shape[-1]) or at least have compatible shape for broadcasting

# Let's use:
# alpha: 1D tensor of size 4
# A: 2D tensor of size (4, 4)

alpha = torch.randn(4)
A = torch.randn(4, 4)

ARGS = {
    "alpha": alpha,
    "A": A
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (4, 4) — shape (4, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_activation Ran
ran; our contract draft was wrong, not the code
zhouc20/HodgeRandomWalk/graphgps/layer/Exphormer.py
code served (permissive licence) · get_code("b888018e8acd3f1d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'activation': 'relu'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_final_pretrained_ckpt Ran
ran; our contract draft was wrong, not the code
zhouc20/HodgeRandomWalk/graphgps/finetuning.py
code served (permissive licence) · get_code("1bb331bf70a78136")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile
import shutil

# Create a temporary directory with checkpoint files
temp_dir = tempfile.mkdtemp()

# Create some checkpoint files with epoch numbers
checkpoint_files = ['1.ckpt', '2.ckpt', '5.ckpt', '3.ckpt']
for ckpt_file in checkpoint_files:
    filepath = os.path.join(temp_dir, ckpt_file)
    with open(filepath, 'w') as f:
        f.write('dummy checkpoint data')

# Define arguments for the function
ARGS = {
    'ckpt_dir': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_log_deg Ran
ran, honoured the contract we drafted
zhouc20/HodgeRandomWalk/graphgps/layer/grit_layer.py
code served (permissive licence) · get_code("b5c9e7acf599a98a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (5, 1) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch_geometric as pyg

torch.manual_seed(0)

# Create a minimal batch object that mimics torch_geometric Data
class MinimalBatch:
    def __init__(self, num_nodes, edge_index):
        self.num_nodes = num_nodes
        self.edge_index = edge_index
    
    def __contains__(self, key):
        return hasattr(self, key)
    
    def __getitem__(self, key):
        return getattr(self, key)

# Create test data
num_nodes = 5
# Edge index: shape [2, num_edges]
edge_index = torch.tensor([
    [0, 1, 2, 3, 1],
    [1, 2, 3, 4, 0]
], dtype=torch.long)

batch = MinimalBatch(num_nodes=num_nodes, edge_index=edge_index)

ARGS = {
    'batch': batch
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torch_geometric — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (5, 1) — shape (5, 1) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
init_model_from_pretrained Ran
ran; our contract draft was wrong, not the code
zhouc20/HodgeRandomWalk/graphgps/finetuning.py
pointer only (licence: MIT); the stored copy get_code serves, from wenkelf/copt, is pointer only (licence: NONE) · get_code("9a4410b8a6c0cc47")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from wenkelf/copt, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

is_seed Ran
ran, violated the contract we drafted
zhouc20/HodgeRandomWalk/graphgps/agg_runs.py
pointer only (licence: MIT); the stored copy get_code serves, from sunjss/over-aggregating, is pointer only (licence: NONE) · get_code("c98a702be0660ac9")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from sunjss/over-aggregating, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

is_split Ran
ran, violated the contract we drafted
zhouc20/HodgeRandomWalk/graphgps/agg_runs.py
pointer only (licence: MIT); the stored copy get_code serves, from sunjss/over-aggregating, is pointer only (licence: NONE) · get_code("438635c08adfe2aa")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from sunjss/over-aggregating, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

join_list Ran
ran, honoured the contract we drafted
zhouc20/HodgeRandomWalk/graphgps/agg_runs.py
pointer only (licence: MIT); the stored copy get_code serves, from sunjss/over-aggregating, is pointer only (licence: NONE) · get_code("40e98e1ecbf39f34")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from sunjss/over-aggregating, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

apply_chunking_to_forward Not yet run
unverified (harvested, no recorded run)
zhouc20/HodgeRandomWalk/graphgps/layer/bigbird_layer.py
pointer only (licence: MIT); the stored copy get_code serves, from sunjss/over-aggregating, is pointer only (licence: NONE) · get_code("ae56bcfaae96da3c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from sunjss/over-aggregating, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

divergence Not yet run
unverified (harvested, no recorded run)
zhouc20/hodgerandomwalk/graphgps/transform/hodge_decomposition.py
code served (permissive licence) · get_code("a0f064817b33d41f")
How it ran

no invocation recorded.

load_pretrained_model_cfg Not yet run
unverified (harvested, no recorded run)
zhouc20/HodgeRandomWalk/graphgps/finetuning.py
pointer only (licence: MIT); the stored copy get_code serves, from ETH-DISCO/Benchmarking-PEs, is pointer only (licence: NONE) · get_code("91c1f5bb90bbe0f3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ETH-DISCO/Benchmarking-PEs, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 11 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 2 the same month, 11 later) and 0 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.

FunctionAlso present inEarliest-datedOthers named
get_final_pretrained_ckpt 27 other papers
7 dated earlier, 1 the same month, 19 later
2302.04181 (2023-02)
Attending to Graph Transformers
2302.08647 (2023-02)
Multiresolution Graph Transformers and Wavelet Positional Encoding for Learning Hierarchical Structures
2305.08018 (2023-05)
DRew: Dynamically Rewired Message Passing with Delay
and 24 more not named here
apply_chunking_to_forward 21 other papers
6 dated earlier, 1 the same month, 14 later
2002.01685 (2020-02)
Parsing as Pretraining
2210.09545 (2022-10)
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
2302.04181 (2023-02)
Attending to Graph Transformers
and 18 more not named here
is_seed 15 other papers
2 dated earlier, 13 later
2302.04181 (2023-02)
Attending to Graph Transformers
2309.00367 (2023-09)
Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark
2312.04234 (2023-12)
Graph Convolutions Enrich the Self-Attention in Transformers!
and 12 more not named here
is_split 15 other papers
2 dated earlier, 13 later
2302.04181 (2023-02)
Attending to Graph Transformers
2309.00367 (2023-09)
Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark
2312.04234 (2023-12)
Graph Convolutions Enrich the Self-Attention in Transformers!
and 12 more not named here
join_list 15 other papers
2 dated earlier, 13 later
2302.04181 (2023-02)
Attending to Graph Transformers
2309.00367 (2023-09)
Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark
2312.04234 (2023-12)
Graph Convolutions Enrich the Self-Attention in Transformers!
and 12 more not named here
load_pretrained_model_cfg 6 other papers
2 dated earlier, 4 later
2305.17589 (2023-05)
Graph Inductive Biases in Transformers without Message Passing
2306.07812 (2023-06)
Automated 3D Pre-Training for Molecular Property Prediction
2402.02518 (2024-02)
Unifying Generation and Prediction on Graphs with Latent Graph Diffusion
and 3 more not named here
get_activation 5 other papers
1 dated earlier, 4 later
2303.06147 (2023-03)
Exphormer: Sparse Transformers for Graphs
2402.02518 (2024-02)
Unifying Generation and Prediction on Graphs with Latent Graph Diffusion
2406.05815 (2024-06)
What Can We Learn from State Space Models for Machine Learning on Graphs?
and 2 more not named here
get_log_deg 5 other papers
1 dated earlier, 4 later
2305.17589 (2023-05)
Graph Inductive Biases in Transformers without Message Passing
2404.03380 (2024-04)
On the Theoretical Expressive Power and the Design Space of Higher-Order Graph Transformers
2404.13604 (2024-04)
CKGConv: General Graph Convolution with Continuous Kernels
and 2 more not named here
init_model_from_pretrained 2 other papers
2 later
2404.03380 (2024-04)
On the Theoretical Expressive Power and the Design Space of Higher-Order Graph Transformers
2405.20543 (2024-05)
Towards a General Recipe for Combinatorial Optimization with Multi-Filter GNNs
Delta_0 1 other paper
1 later
2404.03380 (2024-04)
On the Theoretical Expressive Power and the Design Space of Higher-Order Graph Transformers
divergence 1 other paper
1 later
2404.03380 (2024-04)
On the Theoretical Expressive Power and the Design Space of Higher-Order Graph Transformers

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 2026-11-22.

Repositories linked to this paper

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

Abstract

Node-level random walk has been widely used to improve Graph Neural Networks. However, there is limited attention to random walk on edge and, more generally, on k-simplices. This paper systematically analyzes how random walk on different orders of simplicial complexes (SC) facilitates GNNs in their theoretical expressivity. First, on 0-simplices or node level, we establish a connection between existing positional encoding (PE) and structure encoding (SE) methods through the bridge of random walk. Second, on 1-simplices or edge level, we bridge edge-level random walk and Hodge 1-Laplacians and design corresponding edge PE respectively. In the spatial domain, we directly make use of edge level random walk to construct EdgeRWSE. Based on the spectral analysis of Hodge 1-Laplcians, we propose Hodge1Lap, a permutation equivariant and expressive edge-level positional encoding. Third, we generalize our theory to random walk on higher-order simplices and propose the general principle to design PE on simplices based on random walk and Hodge Laplacians. Inter-level random walk is also introduced to unify a wide range of simplicial networks. Extensive experiments verify the effectiveness of our random walk-based methods.

For agents

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

get_harvested_code_for_paper("2310.19285")
get_code_for_paper("2310.19285")
have("2310.19285")

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

curl https://syntology.ai/api/ran/2310.19285.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.19285.svg)](https://syntology.ai/paper/2310.19285)

Connect an agent — have() is free.