paper-with-me

홈 › Papers

A Causal Disentangled Multi-Granularity Graph Classification Method

2023-10-25 · Yuan Li, Li Liu, Penggang Chen, Youmin Zhang, Guoyin Wang

Graph data widely exists in real life, with large amounts of data and complex structures. It is necessary to map graph data to low-dimensional embedding. Graph classification, a critical graph task, mainly relies on identifying the important substructures within the graph. At present, some graph classification methods do not combine the multi-granularity characteristics of graph data. This lack of granularity distinction in modeling leads to a conflation of key information and false correlations within the model. So, achieving the desired goal of a credible and interpretable model becomes challenging. This paper proposes a causal disentangled multi-granularity graph representation learning method (CDM-GNN) to solve this challenge. The CDM-GNN model disentangles the important substructures and bias parts within the graph from a multi-granularity perspective. The disentanglement of the CDM-GNN model reveals important and bias parts, forming the foundation for its classification task, specifically, model interpretations. The CDM-GNN model exhibits strong classification performance and generates explanatory outcomes aligning with human cognitive patterns. In order to verify the effectiveness of the model, this paper compares the three real-world datasets MUTAG, PTC, and IMDM-M. Six state-of-the-art models, namely GCN, GAT, Top-k, ASAPool, SUGAR, and SAT are employed for comparison purposes. Additionally, a qualitative analysis of the interpretation results is conducted.

📄 PDF Abstract BibTeX arXiv:2310.16256

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationDisentanglementGraph ClassificationGraph Representation LearningRepresentation Learning

Methods 이 논문이 사용한 방법론

GAT A Graph Attention Network (GAT) is a neural network architecture that operates on graph-structured data, leveraging masked self-attentional layers to address the shortcomings…
GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…

Similar Papers 제목 키워드 기반

Which Matters Most in Making Fund Investment Decisions? A Multi-granularity Graph Disentangled Learning Framework

2023-11-23 · Chunjing Gan, Binbin Hu, Bo Huang, Tianyu Zhao 외

In this paper, we highlight that both conformity and risk preference matter in making fund investment decisions beyond personal interest and seek to jointly characterize these aspects in a disentangled manner. Consequent…

Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure

2022-09-28 · Shaohua Fan, Xiao Wang, Yanhu Mo, Chuan Shi 외

Most Graph Neural Networks (GNNs) predict the labels of unseen graphs by learning the correlation between the input graphs and labels. However, by presenting a graph classification investigation on the training graphs wi…

counterfactualGraph Classification

Identifying Coarse-grained Independent Causal Mechanisms with Self-supervision

2021-01-01 · 1st Conference on Causal Learning and Reasoning 2022 2 · Xiaoyang Wang, Klara Nahrstedt, Oluwasanmi O Koyejo

Current approaches for learning disentangled representations assume that independent latent variables generate the data through a single data generation process. In contrast, this manuscript considers independent causal …

Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning

2026-04-21 · Xiangmeng Wang, Qian Li, Haiyang Xia, Hao Miao 외 arxiv

Heterophily is a prevalent property of real-world graphs and is well known to impair the performance of homophilic Graph Neural Networks (GNNs). Prior work has attempted to adapt GNNs to heterophilic graphs through non-l…

Node ClassificationCausal InferenceGraph Learning

Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder

2020-11-24 · Hyemi Kim, Seungjae Shin, JoonHo Jang, Kyungwoo Song 외

The problem of fair classification can be mollified if we develop a method to remove the embedded sensitive information from the classification features. This line of separating the sensitive information is developed thr…

AttributeCausal InferencecounterfactualDisentanglement+1