paper-with-me

홈 › Papers

IMPaCT GNN: Imposing invariance with Message Passing in Chronological split Temporal Graphs

2024-11-17 · Sejun Park, Joo Young Park, Hyunwoo Park

This paper addresses domain adaptation challenges in graph data resulting from chronological splits. In a transductive graph learning setting, where each node is associated with a timestamp, we focus on the task of Semi-Supervised Node Classification (SSNC), aiming to classify recent nodes using labels of past nodes. Temporal dependencies in node connections create domain shifts, causing significant performance degradation when applying models trained on historical data into recent data. Given the practical relevance of this scenario, addressing domain adaptation in chronological split data is crucial, yet underexplored. We propose Imposing invariance with Message Passing in Chronological split Temporal Graphs (IMPaCT), a method that imposes invariant properties based on realistic assumptions derived from temporal graph structures. Unlike traditional domain adaptation approaches which rely on unverifiable assumptions, IMPaCT explicitly accounts for the characteristics of chronological splits. The IMPaCT is further supported by rigorous mathematical analysis, including a derivation of an upper bound of the generalization error. Experimentally, IMPaCT achieves a 3.8% performance improvement over current SOTA method on the ogbn-mag graph dataset. Additionally, we introduce the Temporal Stochastic Block Model (TSBM), which replicates temporal graphs under varying conditions, demonstrating the applicability of our methods to general spatial GNNs.

📄 PDF Abstract BibTeX arXiv:2411.10957

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationGraph LearningNode ClassificationStochastic Block Model

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Accurate and Scalable Graph Neural Networks via Message Invariance

2025-02-27 · Zhihao Shi, Jie Wang, Zhiwei Zhuang, Xize Liang 외

Message passing-based graph neural networks (GNNs) have achieved great success in many real-world applications. For a sampled mini-batch of target nodes, the message passing process is divided into two parts: message pas…

GPUTransductive Learning

Towards Invariance to Node Identifiers in Graph Neural Networks

2025-02-19 · Maya Bechler-Speicher, Moshe Eliasof, Carola-Bibiane Schonlieb, Ran Gilad-Bachrach 외

Message-Passing Graph Neural Networks (GNNs) are known to have limited expressive power, due to their message passing structure. One mechanism for circumventing this limitation is to add unique node identifiers (IDs), wh…

Learning over Positive and Negative Edges with Contrastive Message Passing

2026-05-18 · Peter Pao-Huang, Charilaos I. Kanatsoulis, Michael Bereket, Jure Leskovec arxiv

Conventional approaches to learning on graphs involve message passing along existing (i.e., positive) edges to update node features. However, these approaches often disregard the potentially valuable information containe…

Graph Neural Network

Bond Graphs for multi-physics informed Neural Networks for multi-variate time series

2024-05-22 · Alexis-Raja Brachet, Pierre-Yves Richard, Céline Hudelot

In the trend of hybrid Artificial Intelligence techniques, Physical-Informed Machine Learning has seen a growing interest. It operates mainly by imposing data, learning, or architecture bias with simulation data, Partial…

Graph Neural NetworkInductive BiasMultivariate Time Series ForecastingTime Series+1

Generalization and Representational Limits of Graph Neural Networks

2020-02-14 · ICML 2020 1 · Vikas K. Garg, Stefanie Jegelka, Tommi Jaakkola

We address two fundamental questions about graph neural networks (GNNs). First, we prove that several important graph properties cannot be computed by GNNs that rely entirely on local information. Such GNNs include the s…

Generalization Bounds