SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1806.01973 · 2018

Graph Convolutional Neural Networks for Web-Scale Recommender Systems

Jure Leskovec, Rex Ying, William Hamilton, Kaifeng Chen, Ruining He, Pong Eksombatchai

arXiv · PDF · Open in the Atlas

Code that ran

3 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 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; 8 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/1806.01973.json · badge: /api/ran/1806.01973.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
yoonjong12/pinsage community (classifier label)
classifier basis not recorded on the link
2 ran · 2 no recorded run
breadbread1984/PinSage-tf2.0 community
Papers with Code archive
1 ran · 1 no recorded run
dmlc/dgl community
Papers with Code archive
0 ran · 5 no recorded run
FunctionStatusWhere it lives
Convolve Ran
ran on a synthesized input · constructed an object; no result was computed
breadbread1984/PinSage-tf2.0/PinSage.py
pointer only (licence: NONE) · get_code("96d53e8419ea0290")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, breadbread1984/PinSage-tf2.0 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.

get_blocks Ran
ran on a synthesized input
yoonjong12/pinsage/evaluation.py
code served (permissive licence) · get_code("896a6c529fb43b9d")
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 list, 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)

# Define a minimal sampler class that has the get_block method
class MinimalSampler:
    def get_block(self, seed, item_ntype, textset):
        # Return a simple block object
        return {"seed": seed, "item_ntype": item_ntype, "textset_size": len(textset)}

# Define a minimal textset (can be a list or dict-like object)
class MinimalTextSet:
    def __init__(self):
        self.texts = ["text1", "text2", "text3"]
    
    def __len__(self):
        return len(self.texts)

# Create instances
seeds = [1, 2, 3]
item_ntype = "item"
textset = MinimalTextSet()
sampler = MinimalSampler()

# Define ARGS dict with all parameters
ARGS = {
    "seeds": seeds,
    "item_ntype": item_ntype,
    "textset": textset,
    "sampler": sampler,
}
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 list, ndim 1, dtype family float — a list 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
node_to_item Ran
ran on a synthesized input
yoonjong12/pinsage/evaluation.py
code served (permissive licence) · get_code("302c59855b3fbcec")
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 list, 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 numpy as np

# Construct arguments for node_to_item function
# The function takes node ids and maps them through two dictionaries

# Create id_dict: maps node id -> item category id
id_dict = {
    0: 'cat_a',
    1: 'cat_b',
    2: 'cat_a',
    3: 'cat_c'
}

# Create category_dict: maps item category id -> real item id
category_dict = {
    'cat_a': 'item_001',
    'cat_b': 'item_002',
    'cat_c': 'item_003'
}

# Create nodes: list of node ids
nodes = [0, 1, 2, 3]

ARGS = {
    'nodes': nodes,
    'id_dict': id_dict,
    'cateogry_dict': category_dict
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list 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
DGLError Not yet run
unverified (harvested, no recorded run)
dmlc/dgl/python/dgl/sampling/pinsage.py
code served (permissive licence) · get_code("306abff4458ab700")
How it ran

no invocation recorded.

PinSAGESampler Not yet run
unverified (harvested, no recorded run)
dmlc/dgl/python/dgl/sampling/pinsage.py
code served (permissive licence) · get_code("892b9254565cb7c5")
How it ran

no invocation recorded.

PinSage Not yet run
unverified (harvested, no recorded run)
breadbread1984/PinSage-tf2.0/PinSage.py
pointer only (licence: NONE) · get_code("5557298b5b513f28")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, breadbread1984/PinSage-tf2.0 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.

RandomWalkNeighborSampler Not yet run
unverified (harvested, no recorded run)
dmlc/dgl/python/dgl/sampling/pinsage.py
code served (permissive licence) · get_code("8cbd0b0d003b05e9")
How it ran

no invocation recorded.

_select_pinsage_neighbors Not yet run
unverified (harvested, no recorded run)
dmlc/dgl/python/dgl/sampling/pinsage.py
code served (permissive licence) · get_code("7cacf32da5bfdf02")
How it ran

no invocation recorded.

build_val_test_matrix Not yet run
unverified (harvested, no recorded run)
yoonjong12/pinsage/data_utils.py
code served (permissive licence) · get_code("1eefc35490de45cd")
How it ran

no invocation recorded.

check_param_num Not yet run
unverified (harvested, no recorded run)
yoonjong12/pinsage/evaluation.py
code served (permissive licence) · get_code("dfc097b3bdb4acb8")
How it ran

no invocation recorded.

random_walk Not yet run
unverified (harvested, no recorded run)
dmlc/dgl/python/dgl/sampling/pinsage.py
code served (permissive licence) · get_code("03c3e3f5dfa7773a")
How it ran

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, 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 11 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 advancements in deep neural networks for graph-structured data have led to state-of-the-art performance on recommender system benchmarks. However, making these methods practical and scalable to web-scale recommendation tasks with billions of items and hundreds of millions of users remains a challenge. Here we describe a large-scale deep recommendation engine that we developed and deployed at Pinterest. We develop a dataefficient Graph Convolutional Network (GCN) algorithm PinSage, which combines efficient random walks and graph convolutions to generate embeddings of nodes (i.e., items) that incorporate both graph structure as well as node feature information. Compared to prior GCN approaches, we develop a novel method based on highly efficient random walks to structure the convolutions and design a novel training strategy that relies on harder-and-harder training examples to improve robustness and convergence of the model. We deploy PinSage at Pinterest and train it on 7.5 billion examples on a graph with 3 billion nodes representing pins and boards, and 18 billion edges. According to offline metrics, user studies and A/B tests, PinSage generates higher-quality recommendations than comparable deep learning and graph-based alternatives. To our knowledge, this is the largest application of deep graph embeddings to date and paves the way for a new generation of web-scale recommender systems based on graph convolutional architectures.

For agents

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

get_harvested_code_for_paper("1806.01973")
get_code_for_paper("1806.01973")
have("1806.01973")

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

curl https://syntology.ai/api/ran/1806.01973.json

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

[![Syntology run record](https://syntology.ai/api/ran/1806.01973.svg)](https://syntology.ai/paper/1806.01973)

Connect an agent — have() is free.