paper-with-me

Papers

Improving Subgraph Recognition with Variational Graph Information Bottleneck

2021-12-18 · CVPR 2022 1 · Junchi Yu, Jie Cao, Ran He

Subgraph recognition aims at discovering a compressed substructure of a graph that is most informative to the graph property. It can be formulated by optimizing Graph Information Bottleneck (GIB) with a mutual information estimator. However, GIB suffers from training instability and degenerated results due to its intrinsic optimization process. To tackle these issues, we reformulate the subgraph recognition problem into two steps: graph perturbation and subgraph selection, leading to a novel Variational Graph Information Bottleneck (VGIB) framework. VGIB first employs the noise injection to modulate the information flow from the input graph to the perturbed graph. Then, the perturbed graph is encouraged to be informative to the graph property. VGIB further obtains the desired subgraph by filtering out the noise in the perturbed graph. With the customized noise prior for each input, the VGIB objective is endowed with a tractable variational upper bound, leading to a superior empirical performance as well as theoretical properties. Extensive experiments on graph interpretation, explainability of Graph Neural Networks, and graph classification show that VGIB finds better subgraphs than existing methods. Code is avaliable at https://github.com/Samyu0304/VGIB

📄 PDF Abstract BibTeX arXiv:2112.09899

Code (1)

samyu0304/vgib 공식 구현 pytorch

Tasks

Graph Classification

Similar Papers 제목 키워드 기반

Graph Information Bottleneck for Subgraph Recognition

2020-10-12 · ICLR 2021 1 · Junchi Yu, Tingyang Xu, Yu Rong, Yatao Bian 외

Given the input graph and its label/property, several key problems of graph learning, such as finding interpretable subgraphs, graph denoising and graph compression, can be attributed to the fundamental problem of recogn…

DenoisingGraph ClassificationGraph Learning

Recognizing Predictive Substructures with Subgraph Information Bottleneck

2021-03-20 · Junchi Yu, Tingyang Xu, Yu Rong, Yatao Bian 외

The emergence of Graph Convolutional Network (GCN) has greatly boosted the progress of graph learning. However, two disturbing factors, noise and redundancy in graph data, and lack of interpretation for prediction result…

Bilevel OptimizationGraph Learning

Task-Oriented Communication for Graph Data: A Graph Information Bottleneck Approach

2024-09-04 · Shujing Li, Yanhu Wang, Shuaishuai Guo, Chenyuan Feng

Graph data, essential in fields like knowledge representation and social networks, often involves large networks with many nodes and edges. Transmitting these graphs can be highly inefficient due to their size and redund…

Quantization

Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck

2025-02-20 · Van Thuy Hoang; O-Joun Lee

This study aims to build a pre-trained Graph Neural Network (GNN) model on molecules without human annotations or prior knowledge. Although various attempts have been proposed to overcome limitations in acquiring labeled…

Graph ClassificationGraph Neural NetworkGraph RegressionMolecular Property Prediction+1

Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck

2024-12-20 · Van Thuy Hoang, O-Joun Lee

This study aims to build a pre-trained Graph Neural Network (GNN) model on molecules without human annotations or prior knowledge. Although various attempts have been proposed to overcome limitations in acquiring labeled…

Graph Neural NetworkSelf-Supervised Learning