TS-Extractor: large graph exploration via subgraph extraction based on topological and semantic information

Fu, Kun; Mao, Tingyun; Wang, Yang; Lin, Daoyu; Zhang, Yuanben; Zhan, Junjian; Sun, Xian; Feng, Li

doi:10.1007/s12650-020-00699-y

Cited by 5 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the graph augmentation strategies are for node classification tasks, and heavily focus on perturbing nodes and edges in one given graph (Hamilton, Ying, and Leskovec 2017;Zhang et al 2018b;Chen et al 2020;Zhou, Shen, and Xuan 2020;Qiu et al 2020;You et al 2020;Wang et al 2020b;Fu et al 2020;Wang et al 2020a;Song et al 2021;Zhao et al 2021;Zhao et al 2022;Ding et al 2022;Guo and Sun 2022). Unlike these approaches, our proposed strategy leverages a pair of graphs, instead of one graph, to augment the learning of graph level classification.…”

Section: Related Workmentioning

confidence: 99%

Interpolating Graph Pair to Regularize Graph Classification

Guo

Mao

2023

AAAI

View full text Add to dashboard Cite

We present a simple and yet effective interpolation-based regularization technique, aiming to improve the generalization of Graph Neural Networks (GNNs) on supervised graph classification. We leverage Mixup, an effective regularizer for vision, where random sample pairs and their labels are interpolated to create synthetic images for training. Unlike images with grid-like coordinates, graphs have arbitrary structure and topology, which can be very sensitive to any modification that alters the graph's semantic meanings. This posts two unanswered questions for Mixup-like regularization schemes: Can we directly mix up a pair of graph inputs? If so, how well does such mixing strategy regularize the learning of GNNs? To answer these two questions, we propose ifMixup, which first adds dummy nodes to make two graphs have the same input size and then simultaneously performs linear interpolation between the aligned node feature vectors and the aligned edge representations of the two graphs. We empirically show that such simple mixing schema can effectively regularize the classification learning, resulting in superior predictive accuracy to popular graph augmentation and GNN methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Interpolating Graph Pair to Regularize Graph Classification

Guo

Mao

2023

AAAI

View full text Add to dashboard Cite

show abstract

“…Our work focuses on model-agnostic augmentation, which is to perform augmentation independently from target models. Previous works can be categorized by the purpose of augmentation: node-level tasks [28,38,46], graph-level tasks [10,35,55], or graph contrastive learning [48,49]. Such methods rely on heuristic operations that make no theoretical guarantee for the degree of augmentation or the preservation of graph properties.…”

Section: Related Workmentioning

confidence: 99%

Model-Agnostic Augmentation for Accurate Graph Classification

Yoo¹,

Shim²,

Kang³

2022

Preprint

View full text Add to dashboard Cite

Given a graph dataset, how can we augment it for accurate graph classification? Graph augmentation is an essential strategy to improve the performance of graph-based tasks, and has been widely utilized for analyzing web and social graphs. However, previous works for graph augmentation either a) involve the target model in the process of augmentation, losing the generalizability to other tasks, or b) rely on simple heuristics that lead to unreliable results. In this work, we introduce five desired properties for effective augmentation. Then, we propose NodeSam (Node Split and Merge) and SubMix (Subgraph Mix), two model-agnostic algorithms for graph augmentation that satisfy all desired properties with different motivations. NodeSam makes a balanced change of the graph structure to minimize the risk of semantic change, while SubMix mixes random subgraphs of multiple graphs to create rich soft labels combining the evidence for different classes. Our experiments on social networks and molecular graphs show that NodeSam and SubMix outperform existing approaches in graph classification.

show abstract

“…Nonetheless, graph data augmentation is rather under-explored due to the arbitrary structure and topology in graphs. Most of such strategies heavily focus on perturbing nodes and edges in graphs (Hamilton et al, 2017;Zhang et al, 2018;Rong et al, 2020;Chen et al, 2020;Zhou et al, 2020;Qiu et al, 2020;Fu et al, 2020;Wang et al, 2020;Zhao et al, 2021;Song et al, 2021;Zhao et al, 2021). For example, DropEdge (Rong et al, 2020) randomly removes a set of edges of a given graph.…”

Section: Related Workmentioning

confidence: 99%

SoftEdge: Regularizing Graph Classification with Random Soft Edges

Guo¹,

Sun²

2022

Preprint

View full text Add to dashboard Cite

Graph data augmentation plays a vital role in regularizing Graph Neural Networks (GNNs), which leverage information exchange along edges in graphs, in the form of message passing, for learning. Due to their effectiveness, simple edge and node manipulations (e.g., addition and deletion) have been widely used in graph augmentation. In this paper, we identify a limitation in such a common augmentation technique. That is, simple edge and node manipulations can create graphs with an identical structure or indistinguishable structures to message passing GNNs but of conflict labels, leading to the sample collision issue and thus the degradation of model performance.To address this problem, we propose SoftEdge, which assigns random weights to a portion of the edges of a given graph to construct dynamic neighborhoods over the graph. We prove that SoftEdge creates collision-free augmented graphs. We also show that this simple method obtains superior accuracy to popular node and edge manipulation approaches and notable resilience to the accuracy degradation with the GNN depth.

show abstract

TS-Extractor: large graph exploration via subgraph extraction based on topological and semantic information

Cited by 5 publications

References 39 publications

Interpolating Graph Pair to Regularize Graph Classification

Interpolating Graph Pair to Regularize Graph Classification

Model-Agnostic Augmentation for Accurate Graph Classification

SoftEdge: Regularizing Graph Classification with Random Soft Edges

Contact Info

Product

Resources

About