SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1806.03536 · 2018

Representation Learning on Graphs with Jumping Knowledge Networks

Chengtao Li, Yonglong Tian, Keyulu Xu, Stefanie Jegelka, Ken-Ichi Kawarabayashi, Tomohiro Sonobe

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 0 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/1806.03536.json · badge: /api/ran/1806.03536.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
mori97/JKNet-dgl community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
evaluate Ran
ran on a synthesized input
mori97/JKNet-dgl/train_cora.py
code served (permissive licence) · get_code("ab0a016fefeb5192")
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 float, ndim 0, dtype family float, shape () 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.nn as nn

torch.manual_seed(0)

# Create a minimal graph object that the model can accept
class SimpleGraph:
    def __init__(self):
        self.num_nodes = 2
        self.num_edges = 3

# Create a minimal model that takes graph and xs as input
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)  # 4 input features, 3 output classes
    
    def forward(self, graph, xs):
        # xs shape: (num_nodes, 4)
        # output shape: (num_nodes, 3)
        return self.linear(xs)

# Create instances
graph = SimpleGraph()
model = SimpleModel()

# Create xs tensor: (2, 4) - 2 nodes with 4 features each
xs = torch.randn(2, 4)

# Create idx_test: indices to select from the model output
# Should be a subset or all indices
idx_test = torch.tensor([0, 1])

# Create ts_test: ground truth labels for test set
# Should have same length as idx_test and values in range [0, 2] for 3 classes
ts_test = torch.tensor([0, 2])

ARGS = {
    "graph": graph,
    "model": model,
    "xs": xs,
    "idx_test": idx_test,
    "ts_test": ts_test
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () 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

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 2026-11-22.

Repositories linked to this paper

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

Abstract

Recent deep learning approaches for representation learning on graphs follow a neighborhood aggregation procedure. We analyze some important properties of these models, and propose a strategy to overcome those. In particular, the range of "neighboring" nodes that a node's representation draws from strongly depends on the graph structure, analogous to the spread of a random walk. To adapt to local neighborhood properties and tasks, we explore an architecture -jumping knowledge (JK) networks -that flexibly leverages, for each node, different neighborhood ranges to enable better structure-aware representation. In a number of experiments on social, bioinformatics and citation networks, we demonstrate that our model achieves state-of-the-art performance. Furthermore, combining the JK framework with models like Graph Convolutional Networks, GraphSAGE and Graph Attention Networks consistently improves those models' performance.

For agents

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

get_harvested_code_for_paper("1806.03536")
get_code_for_paper("1806.03536")
have("1806.03536")

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

curl https://syntology.ai/api/ran/1806.03536.json

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

[![Syntology run record](https://syntology.ai/api/ran/1806.03536.svg)](https://syntology.ai/paper/1806.03536)

Connect an agent — have() is free.