SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.02172 · ICML · 2022

Learning from Counterfactual Links for Link Prediction

Tong Zhao, Gang Liu, Daheng Wang, Wenhao Yu, Meng Jiang, Alice Adam, Bob Helen, Encoder Gnn, Decoder

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2106.02172.json · badge: /api/ran/2106.02172.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
DM2-ND/CFLP marked official in Papers with Code
Papers with Code archive
3 ran · 0 no recorded run
FunctionStatusWhere it lives
CFLP Ran
ran on a synthesized input · constructed an object; no result was computed
DM2-ND/CFLP/models.py
code served (permissive licence) · get_code("8998798cdcc4de8d")
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 an instance of its own class, CFLP: the run constructed the object and did not call it, so no result was computed. 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 torch
import torch.nn as nn
import torch.nn.functional as F
from torch_geometric.nn import GCNConv, SAGEConv, JumpingKnowledge

torch.manual_seed(0)

# Create minimal valid arguments for CFLP forward pass
num_nodes = 4
dim_feat = 5
dim_h = 8
dim_z = 6
dropout = 0.1
gnn_type = 'GCN'
jk_mode = 'mean'
dec = 'hadamard'

ARGS = {
    'dim_feat': dim_feat,
    'dim_h': dim_h,
    'dim_z': dim_z,
    'dropout': dropout,
    'gnn_type': gnn_type,
    'jk_mode': jk_mode,
    'dec': dec,
}
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 CFLP — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a CFLP 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
Decoder Ran
ran on a synthesized input · constructed an object; no result was computed
DM2-ND/CFLP/models.py
code served (permissive licence) · get_code("70bbd05e3696b199")
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 an instance of its own class, Decoder: the run constructed the object and did not call it, so no result was computed. 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 torch
import torch.nn as nn

torch.manual_seed(0)

class Decoder(nn.Module):

    def __init__(self, dec, dim_z, dim_h=64):
        super(Decoder, self).__init__()
        self.dec = dec
        if dec == 'innerproduct':
            dim_in = 2
        elif dec == 'hadamard':
            dim_in = dim_z + 1
        elif dec == 'mlp':
            dim_in = 1 + 2 * dim_z
        self.mlp_out = nn.Sequential(nn.Linear(dim_in, dim_h, bias=True), nn.ELU(), nn.Dropout(), nn.Linear(dim_h, 1, bias=False))

    def forward(self, z_i, z_j, T):
        if self.dec == 'innerproduct':
            z = (z_i * z_j).sum(1).view(-1, 1)
            h = torch.cat((z, T.view(-1, 1)), dim=1)
        elif self.dec == 'mlp':
            h = torch.cat((z_i, z_j, T.view(-1, 1)), dim=1)
        elif self.dec == 'hadamard':
            z = z_i * z_j
            h = torch.cat((z, T.view(-1, 1)), dim=1)
        h = self.mlp_out(h).squeeze()
        return h

    def reset_parameters(self):
        for lin in self.mlp_out:
            try:
                lin.reset_parameters()
            except:
                continue

# Create test tensors
batch_size = 2
dim_z = 4

z_i = torch.randn(batch_size, dim_z)
z_j = torch.randn(batch_size, dim_z)
T = torch.randn(batch_size)

# Test with 'mlp' decoder
decoder_instance = Decoder(dec='mlp', dim_z=dim_z, dim_h=64)

ARGS = {
    'dec': 'mlp',
    'dim_z': dim_z,
    'dim_h': 64
}
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 Decoder — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Decoder 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
GNN Ran
ran on a synthesized input · constructed an object; no result was computed
DM2-ND/CFLP/models.py
code served (permissive licence) · get_code("012be499f262ee24")
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 an instance of its own class, GNN: the run constructed the object and did not call it, so no result was computed. 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 torch
import torch.nn as nn
from torch_geometric.nn import GCNConv

torch.manual_seed(0)

# Create a small adjacency matrix (edge index format for PyG)
# For a graph with 2 nodes, we need edge indices
adj = torch.tensor([[0, 1], [1, 0]], dtype=torch.long).t().contiguous()

# Create feature matrix: 2 nodes, 4 features each
features = torch.randn(2, 4)

ARGS = {
    'dim_feat': 4,
    'dim_h': 3,
    'dim_z': 5,
    'dropout': 0.5,
    'gnn_type': 'GCN',
    'num_layers': 3,
    'jk_mode': 'mean',
    'batchnorm': True,
}
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 GNN — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a GNN 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Learning to predict missing links is important for many graph-based applications. Existing methods were designed to learn the association between observed graph structure and existence of link between a pair of nodes. However, the causal relationship between the two variables was largely ignored for learning to predict links on a graph. In this work, we visit this factor by asking a counterfactual question: "would the link still exist if the graph structure became different from observation?" Its answer, counterfactual links, will be able to augment the graph data for representation learning. To create these links, we employ causal models that consider the information (i.e., learned representations) of node pairs as context, global graph structural properties as treatment, and link existence as outcome. We propose a novel data augmentation-based link prediction method that creates counterfactual links and learns representations from both the observed and counterfactual links. Experiments on benchmark data show that our graph learning method achieves state-of-theart performance on the task of link prediction.

For agents

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

get_harvested_code_for_paper("2106.02172")
get_code_for_paper("2106.02172")
have("2106.02172")

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

curl https://syntology.ai/api/ran/2106.02172.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.02172.svg)](https://syntology.ai/paper/2106.02172)

Connect an agent — have() is free.