Differentiable Cluster Graph Neural Network
원문 초록
Graph Neural Networks often struggle with long-range information propagation and in the presence of heterophilous neighborhoods. We address both challenges with a unified framework that incorporates a clustering inductive bias into the message passing mechanism, using additional cluster-nodes. Central to our approach is the formulation of an optimal transport based implicit clustering objective function. However, the algorithm for solving the implicit objective function needs to be differentiable to enable end-to-end learning of the GNN. To facilitate this, we adopt an entropy regularized objective function and propose an iterative optimization process, alternating between solving for the cluster assignments and updating the node/cluster-node embeddings. Notably, our derived closed-form optimization steps are themselves simple yet elegant message passing steps operating seamlessly on a bipartite graph of nodes and cluster-nodes. Our clustering-based approach can effectively capture both local and global information, demonstrated by extensive experiments on both heterophilous and homophilous datasets.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Learning to cluster neuronal function
GNN-ViTCap: GNN-Enhanced Multiple Instance Learning with Vision Transformers for Whole Slide Image Classification and Captioning
Directed Acyclic Graph Convolutional Networks
GraphFLEx: Structure Learning Framework for Large Expanding Graphs
Fuzzy Graph Neural Network for Few-Shot Learning
MRAEA: An Efficient and Robust Entity Alignment Approach for Cross-lingual Knowledge Graph
토론
이 논문과 연결된 포럼 글이 아직 없습니다.