paper-with-me

Papers

MxPool: Multiplex Pooling for Hierarchical Graph Representation Learning

2020-04-15 · ICLR 2020 1 · Yanyan Liang, Yanfeng Zhang, Dechao Gao, Qian Xu

How to utilize deep learning methods for graph classification tasks has attracted considerable research attention in the past few years. Regarding graph classification tasks, the graphs to be classified may have various graph sizes (i.e., different number of nodes and edges) and have various graph properties (e.g., average node degree, diameter, and clustering coefficient). The diverse property of graphs has imposed significant challenges on existing graph learning techniques since diverse graphs have different best-fit hyperparameters. It is difficult to learn graph features from a set of diverse graphs by a unified graph neural network. This motivates us to use a multiplex structure in a diverse way and utilize a priori properties of graphs to guide the learning. In this paper, we propose MxPool, which concurrently uses multiple graph convolution/pooling networks to build a hierarchical learning structure for graph representation learning tasks. Our experiments on numerous graph classification benchmarks show that our MxPool has superiority over other state-of-the-art graph representation learning methods.

📄 PDF Abstract BibTeX arXiv:2004.06846

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationClusteringGeneral ClassificationGraph ClassificationGraph LearningGraph Neural NetworkGraph Representation LearningRepresentation Learning

Similar Papers 제목 키워드 기반

A Geometric Perspective for High-Dimensional Multiplex Graphs

2025-01-29 · Kamel Abdous, Nairouz Mrabah, Mohamed Bouguessa

High-dimensional multiplex graphs are characterized by their high number of complementary and divergent dimensions. The existence of multiple hierarchical latent relations between the graph dimensions poses significant c…

Graph Embedding

Graph Pooling with Node Proximity for Hierarchical Representation Learning

2020-06-19 · Xing Gao, Wenrui Dai, Chenglin Li, Hongkai Xiong 외

Graph neural networks have attracted wide attentions to enable representation learning of graph data in recent works. In complement to graph convolution operators, graph pooling is crucial for extracting hierarchical rep…

Graph ClassificationRepresentation Learning

CommPOOL: An Interpretable Graph Pooling Framework for Hierarchical Graph Representation Learning

2020-12-10 · Haoteng Tang, Guixiang Ma, Lifang He, Heng Huang 외

Recent years have witnessed the emergence and flourishing of hierarchical graph pooling neural networks (HGPNNs) which are effective graph representation learning approaches for graph level tasks such as graph classifica…

Graph ClassificationGraph Representation LearningRepresentation Learning

Hierarchical Graph Pooling with Structure Learning

2019-11-14 · Zhen Zhang, Jiajun Bu, Martin Ester, Jianfeng Zhang 외

Graph Neural Networks (GNNs), which generalize deep neural networks to graph-structured data, have drawn considerable attention and achieved state-of-the-art performance in numerous graph related tasks. However, existing…

Graph ClassificationGraph Neural NetworkRepresentation Learning

Hierarchical Aggregations for High-Dimensional Multiplex Graph Embedding

2023-12-28 · Kamel Abdous, Nairouz Mrabah, Mohamed Bouguessa

We investigate the problem of multiplex graph embedding, that is, graphs in which nodes interact through multiple types of relations (dimensions). In recent years, several methods have been developed to address this prob…

Graph EmbeddingLink PredictionNode Classification