paper-with-me

홈 › Papers

GNN-VPA: A Variance-Preserving Aggregation Strategy for Graph Neural Networks

2024-03-07 · Lisa Schneckenreiter, Richard Freinschlag, Florian Sestak, Johannes Brandstetter, Günter Klambauer, Andreas Mayr

Graph neural networks (GNNs), and especially message-passing neural networks, excel in various domains such as physics, drug discovery, and molecular modeling. The expressivity of GNNs with respect to their ability to discriminate non-isomorphic graphs critically depends on the functions employed for message aggregation and graph-level readout. By applying signal propagation theory, we propose a variance-preserving aggregation function (VPA) that maintains expressivity, but yields improved forward and backward dynamics. Experiments demonstrate that VPA leads to increased predictive performance for popular GNN architectures as well as improved learning dynamics. Our results could pave the way towards normalizer-free or self-normalizing GNNs.

📄 PDF Abstract BibTeX arXiv:2403.04747

Code (1)

ml-jku/gnn-vpa 공식 구현 pytorch

Tasks

Drug Discovery

Similar Papers 제목 키워드 기반

Graph Attribute Aggregation Network with Progressive Margin Folding

2019-05-14 · Penghui Sun, Jingwei Qu, Xiaoqing Lyu, Haibin Ling 외

Graph convolutional neural networks (GCNNs) have been attracting increasing research attention due to its great potential in inference over graph structures. However, insufficient effort has been devoted to the aggregati…

Attribute

Orientation covariant aggregation of local descriptors with embeddings

2014-07-08 · Giorgos Tolias, Teddy Furon, Hervé Jégou

Image search systems based on local descriptors typically achieve orientation invariance by aligning the patches on their dominant orientations. Albeit successful, this choice introduces too much invariance because it do…

Image RetrievalRetrieval

Breaking the Expressive Bottlenecks of Graph Neural Networks

2020-12-14 · Mingqi Yang, Yanming Shen, Heng Qi, BaoCai Yin

Recently, the Weisfeiler-Lehman (WL) graph isomorphism test was used to measure the expressiveness of graph neural networks (GNNs), showing that the neighborhood aggregation GNNs were at most as powerful as 1-WL test in …

Graph Property Prediction

FedGraph: an Aggregation Method from Graph Perspective

2022-10-06 · Zhifang Deng, Xiaohong Huang, Dandan Li, Xueguang Yuan

With the increasingly strengthened data privacy act and the difficult data centralization, Federated Learning (FL) has become an effective solution to collaboratively train the model while preserving each client's privac…

Federated LearningTumor Segmentation

Federated Domain Generalization with Latent Space Inversion

2025-12-11 · Ragja Palakkadavath, Hung Le, Thanh Nguyen-Tang, Svetha Venkatesh 외 arxiv

Federated domain generalization (FedDG) addresses distribution shifts among clients in a federated learning framework. FedDG methods aggregate the parameters of locally trained client models to form a global model that g…

Domain GeneralizationFederated Learning