SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.09953 · 2024

Through the Dual-Prism: A Spectral Perspective on Graph Data Augmentation for Graph Classification

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
yu-rp/dualprism canonical 6 of 10
FunctionStatusWhere it lives
add_noise Ran yu-rp/dualprism/src/aug.py
pointer only (licence: NONE) · get_code("ae4f1bded5dc4c34")
generate_threshold_vector Ran yu-rp/dualprism/src/aug.py
pointer only (licence: NONE) · get_code("a61699b46d3d13d8")
graph_numpy2tensor Ran yu-rp/dualprism/src/utils.py
pointer only (licence: NONE) · get_code("0b1f01b346d86095")
prepare_dataset Ran yu-rp/dualprism/src/utils.py
pointer only (licence: NONE) · get_code("cbf4d0892481c707")
prepare_synthetic_dataset Ran yu-rp/dualprism/src/utils.py
pointer only (licence: NONE) · get_code("7a73d187862ecb75")
triplet_loss Ran yu-rp/dualprism/DIG/dig/auggraph/method/DualPrism/utils/utils.py
pointer only (licence: NONE) · get_code("c6e56bc4d0f6bab6")
approximate_hamming_similarity Not yet run yu-rp/dualprism/DIG/dig/auggraph/method/DualPrism/utils/utils.py
pointer only (licence: NONE) · get_code("95afc6f0962b5c2a")
euclidean_distance Not yet run yu-rp/dualprism/DIG/dig/auggraph/method/DualPrism/utils/utils.py
pointer only (licence: NONE) · get_code("69e7dcdc10127913")
spectral_noise Not yet run yu-rp/dualprism/src/aug.py
pointer only (licence: NONE) · get_code("983c6560bfc8086d")
spectral_noise Not yet run yu-rp/dualprism/DIG/dig/auggraph/method/DualPrism/utils/augmentation.py
pointer only (licence: NONE) · get_code("34cc38b600742cf0")

Repositories linked to this paper

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

Abstract

Graph Neural Networks have become the preferred tool to process graph data, with their efficacy being boosted through graph data augmentation techniques. Despite the evolution of augmentation methods, issues like graph property distortions and restricted structural changes persist. This leads to the question: Is it possible to develop more property-conserving and structure-sensitive augmentation methods? Through a spectral lens, we investigate the interplay between graph properties, their augmentation, and their spectral behavior, and observe that keeping the low-frequency eigenvalues unchanged can preserve the critical properties at a large scale when generating augmented graphs. These observations inform our introduction of the Dual-Prism (DP) augmentation methods, including DP-Noise and DP-Mask, which retain essential graph properties while diversifying augmented graphs. Extensive experiments validate the efficiency of our approach, providing a new and promising direction for graph data augmentation.

For agents

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

get_harvested_code_for_paper("2401.09953")
get_code_for_paper("2401.09953")
have("2401.09953")

Connect an agent — have() is free.