SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.03665 · 2020

AnomalyDAE: Dual autoencoder for anomaly detection on attributed networks

arXiv · PDF · Open in the Atlas

Code that ran

8 of 14 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, 0 violated it and 3 have no contract verdict; 3 failures of our instrument; 6 no recorded run), measured 2026-11-21; 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/2002.03665.json · badge: /api/ran/2002.03665.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
haoyfan/AnomalyDAE canonical (classifier label)
classifier basis: census
8 ran · 6 no recorded run
FunctionStatusWhere it lives
construct_feed_dict Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
haoyfan/AnomalyDAE/src/preprocessing.py
pointer only (licence: MIT); the stored copy get_code serves, from sigvae/SIGraphVAE, is pointer only (licence: NONE) · get_code("b959bc9ff832fac0")
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 sigvae/SIGraphVAE, 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.

get_layer_uid Ran
ran, honoured the contract we drafted
haoyfan/AnomalyDAE/src/layers.py
pointer only (licence: MIT); the stored copy get_code serves, from sigvae/SIGraphVAE, is pointer only (licence: NONE) · get_code("addac9c28c065096")
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 sigvae/SIGraphVAE, 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.

get_model Ran
ran on a synthesized input
haoyfan/AnomalyDAE/src/constructor.py
code served (permissive licence) · get_code("4aa3113618366c59")
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 MockGCNModelAE. 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 MockGCNModelAE(nn.Module):
    def __init__(self, placeholders, num_features, features_nonzero):
        super().__init__()
        self.placeholders = placeholders
        self.num_features = num_features
        self.features_nonzero = features_nonzero
    
    def forward(self, x):
        return x

class MockAnomalyDAE(nn.Module):
    def __init__(self, placeholders, num_features, num_nodes, features_nonzero):
        super().__init__()
        self.placeholders = placeholders
        self.num_features = num_features
        self.num_nodes = num_nodes
        self.features_nonzero = features_nonzero
    
    def forward(self, x):
        return x

# Mock the imported classes in the module namespace
import sys
current_module = sys.modules[__name__]
current_module.GCNModelAE = MockGCNModelAE
current_module.AnomalyDAE = MockAnomalyDAE

# Create placeholders dict with typical graph neural network structure
placeholders = {
    'features': torch.randn(2, 4),
    'adj': torch.randn(2, 2),
    'adj_norm': torch.randn(2, 2),
    'dropout': 0.5,
}

num_features = 4
num_nodes = 2
features_nonzero = 8

ARGS = {
    'model_str': 'gcn_ae',
    'placeholders': placeholders,
    'num_features': num_features,
    'num_nodes': num_nodes,
    'features_nonzero': features_nonzero,
}
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 MockGCNModelAE — a MockGCNModelAE output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MockGCNModelAE 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
parse_index_file Ran
ran, honoured the contract we drafted
haoyfan/AnomalyDAE/src/input_data.py
code served (permissive licence) · get_code("5c3fa9402a9405bc")
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 list, ndim 1, dtype family int; 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 tempfile
import os

# Create a temporary file with index data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("0\n")
temp_file.write("1\n")
temp_file.write("5\n")
temp_file.write("3\n")
temp_file.close()

ARGS = {
    "filename": temp_file.name
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 int — 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
precision_AT_K Ran
ran on a synthesized input
haoyfan/AnomalyDAE/src/utils.py
code served (permissive licence) · get_code("2a37ab315cc44c1f")
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 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 numpy as np

# Create small numpy arrays for actual and predicted
# These represent binary indicators of anomalies
# actual and predicted should be lists/arrays of binary values (0 or 1)
actual = np.array([1, 0, 1, 1, 0, 1, 0, 0])
predicted = np.array([1, 1, 0, 1, 0, 1, 1, 0])

# k is the cutoff parameter
k = 5

# num_anomaly is the total number of anomalies in the actual data
num_anomaly = 4

ARGS = {
    "actual": actual,
    "predicted": predicted,
    "k": k,
    "num_anomaly": num_anomaly
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — 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
preprocess_graph Ran
ran; our contract draft was wrong, not the code
haoyfan/AnomalyDAE/src/preprocessing.py
pointer only (licence: MIT); the stored copy get_code serves, from sigvae/SIGraphVAE, is pointer only (licence: NONE) · get_code("20362feefced8682")
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 sigvae/SIGraphVAE, 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.

read_results Ran
ran on a synthesized input
haoyfan/AnomalyDAE/src/utils.py
code served (permissive licence) · get_code("15b42e9e4ecb7c9e")
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 json
import tempfile
import os

# Create a temporary JSON file with sample results
temp_dir = tempfile.mkdtemp()
export_json_path = os.path.join(temp_dir, "results.json")

sample_results = {
    "accuracy": 0.95,
    "loss": 0.05,
    "epochs": 10,
    "metrics": {
        "precision": 0.92,
        "recall": 0.93
    }
}

with open(export_json_path, 'w') as fp:
    json.dump(sample_results, fp)

ARGS = {
    "export_json": export_json_path
}
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 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
sparse_to_tuple Ran
ran; our contract draft was wrong, not the code
haoyfan/AnomalyDAE/src/preprocessing.py
pointer only (licence: MIT); the stored copy get_code serves, from mocherson/MedGCN, is pointer only (licence: NONE) · get_code("3965c8f8e2d0023e")
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 mocherson/MedGCN, 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.

dropout_sparse Not yet run
unverified (harvested, no recorded run)
haoyfan/AnomalyDAE/src/layers.py
code served (permissive licence) · get_code("1aae0eaba6789dd0")
How it ran

no invocation recorded.

get_optimizer Not yet run
unverified (harvested, no recorded run)
haoyfan/AnomalyDAE/src/constructor.py
code served (permissive licence) · get_code("36ff1ea6caee0d82")
How it ran

no invocation recorded.

load_data Not yet run
unverified (harvested, no recorded run)
haoyfan/AnomalyDAE/src/input_data.py
code served (permissive licence) · get_code("c737344613561576")
How it ran

no invocation recorded.

load_data2 Not yet run
unverified (harvested, no recorded run)
haoyfan/AnomalyDAE/src/input_data.py
code served (permissive licence) · get_code("cfae20fa9bfcbefb")
How it ran

no invocation recorded.

precision_AT_K Not yet run
unverified (harvested, no recorded run)
haoyfan/AnomalyDAE/src/anomaly_detection.py
code served (permissive licence) · get_code("fce5c0c2d1eb87e9")
How it ran

no invocation recorded.

weight_variable_glorot Not yet run
unverified (harvested, no recorded run)
haoyfan/AnomalyDAE/src/initializations.py
code served (permissive licence) · get_code("8a99ee5c26e527fa")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 2 the same month, 5 later) and 6 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
parse_index_file 53 other papers
21 dated earlier, 2 the same month, 30 later · 1 only as an assembly brick
1603.08861 (2016-03)
Revisiting Semi-Supervised Learning with Graph Embeddings
1611.07308 (2016-11)
Variational Graph Auto-Encoders
1710.10568 (2017-10)
Stochastic Training of Graph Convolutional Networks with Variance Reduction
and 50 more not named here
get_layer_uid 33 other papers
21 dated earlier, 1 the same month, 11 later · 5 only as an assembly brick
1603.08861 (2016-03)
Revisiting Semi-Supervised Learning with Graph Embeddings
1606.09375 (2016-06)
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
1609.02907 (2016-09)
Semi-Supervised Classification with Graph Convolutional Networks
and 30 more not named here
sparse_to_tuple 9 other papers
5 dated earlier, 4 later
1611.07308 (2016-11)
Variational Graph Auto-Encoders
1804.00099 (2018-04)
Graph Convolutional Neural Networks via Scattering
1904.00326 (2019-04)
MedGCN: Medication recommendation and lab test imputation via graph convolutional networks
and 6 more not named here
construct_feed_dict 4 other papers
3 dated earlier, 1 later
1611.07308 (2016-11)
Variational Graph Auto-Encoders
1906.05017 (2019-06)
Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations
1908.07078 (2019-08)
Semi-Implicit Graph Variational Auto-Encoders
and 1 more not named here
dropout_sparse 3 other papers
2 dated earlier, 1 later
1611.07308 (2016-11)
Variational Graph Auto-Encoders
1906.05017 (2019-06)
Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations
ijcai2022_0498 (2022 (year only))
Stabilizing and Enhancing Link Prediction through Deepened Graph Auto-Encoders
preprocess_graph 3 other papers
3 dated earlier
1611.07308 (2016-11)
Variational Graph Auto-Encoders
1906.05017 (2019-06)
Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations
1908.07078 (2019-08)
Semi-Implicit Graph Variational Auto-Encoders
weight_variable_glorot 2 other papers
2 dated earlier
1611.07308 (2016-11)
Variational Graph Auto-Encoders
1906.05017 (2019-06)
Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Anomaly detection on attributed networks aims at finding nodes whose patterns deviate significantly from the majority of reference nodes, which is pervasive in many applications such as network intrusion detection and social spammer detection. However, most existing methods neglect the complex cross-modality interactions between network structure and node attribute. In this paper, we propose a deep joint representation learning framework for anomaly detection through a dual autoencoder (AnomalyDAE), which captures the complex interactions between network structure and node attribute for high-quality embeddings. Specifically, AnomalyDAE consists of a structure autoencoder and an attribute autoencoder to learn both node embedding and attribute embedding jointly in latent space. Moreover, attention mechanism is employed in structure encoder to learn the importance between a node and its neighbors for an effective capturing of structure pattern, which is important to anomaly detection. Besides, by taking both the node embedding and attribute embedding as inputs of attribute decoder, the cross-modality interactions between network structure and node attribute are learned during the reconstruction of node attribute. Finally, anomalies can be detected by measuring the reconstruction errors of nodes from both the structure and attribute perspectives. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed method.

For agents

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

get_harvested_code_for_paper("2002.03665")
get_code_for_paper("2002.03665")
have("2002.03665")

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

curl https://syntology.ai/api/ran/2002.03665.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.03665.svg)](https://syntology.ai/paper/2002.03665)

Connect an agent — have() is free.