SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1903.00757 · 2019

GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embedding

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 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 4 have no contract verdict; 0 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/1903.00757.json · badge: /api/ran/1903.00757.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
DeepGraphLearning/graphvite community (classifier label)
classifier basis not recorded on the link
4 ran · 3 no recorded run
FunctionStatusWhere it lives
find_all_names Ran
ran on a synthesized input
DeepGraphLearning/graphvite/python/graphvite/helper.py
code served (permissive licence) · get_code("78c4c05ac8ba1a72")
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 re

class MockModule:
    def __init__(self):
        self.valid_name = "value1"
        self.another_name = "value2"
        self._private_name = "value3"
        self.__dunder__ = "value4"
        self.test_attribute = 42

module = MockModule()

ARGS = {
    'module': module
}
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 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
find_all_templates Ran
ran on a synthesized input
DeepGraphLearning/graphvite/python/graphvite/helper.py
code served (permissive licence) · get_code("801fb64b0497c90c")
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 re

class MockModule:
    def __init__(self):
        self.simple_name = "value1"
        self.compound_name_with_underscores = "value2"
        self.another_compound_name_here = "value3"
        self.single = "value4"
        self.multi_part_name_test = "value5"
        self.x_y_z = "value6"

module = MockModule()

ARGS = {
    "module": module
}
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 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
recursive_default Ran
ran on a synthesized input
DeepGraphLearning/graphvite/python/graphvite/util.py
code served (permissive licence) · get_code("29ce96b8f084f58d")
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 dict. 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 numpy as np

torch.manual_seed(0)

# The function recursive_default takes two parameters:
# - obj: an object (can be a dict or other type)
# - default: a dict or other type used as a template/default structure
#
# The function recursively applies defaults from the 'default' parameter
# to the 'obj' parameter. If default is a dict, it iterates through keys,
# recursively calling itself on matching keys in obj, or using the default value.
# Otherwise it returns obj as-is.

# Test case 1: obj is a dict, default is a dict (the main recursive case)
obj = {
    "a": 1,
    "b": {
        "c": 2
    }
}

default = {
    "a": 10,
    "b": {
        "c": 20,
        "d": 30
    },
    "e": 40
}

ARGS = {
    "obj": obj,
    "default": default
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
recursive_map Ran
ran on a synthesized input
DeepGraphLearning/graphvite/python/graphvite/util.py
code served (permissive licence) · get_code("7264853b8d0e9cd8")
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 dict. 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 numpy as np

torch.manual_seed(0)

# Define a simple function to apply recursively
def increment_func(x):
    if isinstance(x, (int, float)):
        return x + 1
    elif isinstance(x, torch.Tensor):
        return x + 1
    elif isinstance(x, np.ndarray):
        return x + 1
    else:
        return x

# Create test data structures with mixed types
test_tensor = torch.tensor([1.0, 2.0, 3.0, 4.0])
test_array = np.array([1, 2, 3, 4])
test_scalar = 5

# Build a complex nested structure with dict and list
nested_obj = {
    "tensor": test_tensor,
    "scalar": test_scalar,
    "nested_list": [1, 2, test_array],
    "nested_dict": {
        "value": 10,
        "array": np.array([5, 6, 7]),
    }
}

ARGS = {
    "obj": nested_obj,
    "function": increment_func
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
assert_in Not yet run
unverified (harvested, no recorded run)
DeepGraphLearning/graphvite/python/graphvite/util.py
code served (permissive licence) · get_code("81f9cf448d698eaf")
How it ran

no invocation recorded.

signature Not yet run
unverified (harvested, no recorded run)
DeepGraphLearning/graphvite/python/graphvite/helper.py
code served (permissive licence) · get_code("4a22f661535c9d9d")
How it ran

no invocation recorded.

triplet_prediction Not yet run
unverified (harvested, no recorded run)
DeepGraphLearning/graphvite/python/graphvite/application/application.py
code served (permissive licence) · get_code("73fee353b6999f32")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 7 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 continuous representations of nodes is attracting growing interest in both academia and industry recently, due to their simplicity and effectiveness in a variety of applications. Most of existing node embedding algorithms and systems are capable of processing networks with hundreds of thousands or a few millions of nodes. However, how to scale them to networks that have tens of millions or even hundreds of millions of nodes remains a challenging problem. In this paper, we propose GraphVite, a high-performance CPU-GPU hybrid system for training node embeddings, by co-optimizing the algorithm and the system. On the CPU end, augmented edge samples are parallelly generated by random walks in an online fashion on the network, and serve as the training data. On the GPU end, a novel parallel negative sampling is proposed to leverage multiple GPUs to train node embeddings simultaneously, without much data transfer and synchronization. Moreover, an efficient collaboration strategy is proposed to further reduce the synchronization cost between CPUs and GPUs. Experiments on multiple real-world networks show that GraphVite is super efficient. It takes only about one minute for a network with 1 million nodes and 5 million edges on a single machine with 4 GPUs, and takes around 20 hours for a network with 66 million nodes and 1.8 billion edges. Compared to the current fastest system, GraphVite is about 50 times faster without any sacrifice on performance.

For agents

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

get_harvested_code_for_paper("1903.00757")
get_code_for_paper("1903.00757")
have("1903.00757")

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

curl https://syntology.ai/api/ran/1903.00757.json

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

[![Syntology run record](https://syntology.ai/api/ran/1903.00757.svg)](https://syntology.ai/paper/1903.00757)

Connect an agent — have() is free.