Learning from Heterogeneity: A Dynamic Learning Framework for Hypergraphs

by   Tiehua Zhang, et al.

Graph neural network (GNN) has gained increasing popularity in recent years owing to its capability and flexibility in modeling complex graph structure data. Among all graph learning methods, hypergraph learning is a technique for exploring the implicit higher-order correlations when training the embedding space of the graph. In this paper, we propose a hypergraph learning framework named LFH that is capable of dynamic hyperedge construction and attentive embedding update utilizing the heterogeneity attributes of the graph. Specifically, in our framework, the high-quality features are first generated by the pairwise fusion strategy that utilizes explicit graph structure information when generating initial node embedding. Afterwards, a hypergraph is constructed through the dynamic grouping of implicit hyperedges, followed by the type-specific hypergraph learning process. To evaluate the effectiveness of our proposed framework, we conduct comprehensive experiments on several popular datasets with eleven state-of-the-art models on both node classification and link prediction tasks, which fall into categories of homogeneous pairwise graph learning, heterogeneous pairwise graph learning, and hypergraph learning. The experiment results demonstrate a significant performance gain (average 12.5 node classification and 13.3 state-of-the-art methods.


A Hypergraph Neural Network Framework for Learning Hyperedge-Dependent Node Embeddings

In this work, we introduce a hypergraph representation learning framewor...

Exploiting Spatial-temporal Data for Sleep Stage Classification via Hypergraph Learning

Sleep stage classification is crucial for detecting patients' health con...

DualHGNN: A Dual Hypergraph Neural Network for Semi-Supervised Node Classification based on Multi-View Learning and Density Awareness

Graph-based semi-supervised node classification has been shown to become...

You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks

Hypergraphs are used to model higher-order interactions amongst agents a...

Love tHy Neighbour: Remeasuring Local Structural Node Similarity in Hypergraph-Derived Networks

The problem of node-similarity in networks has motivated a plethora of s...

Hyper-GST: Predict Metro Passenger Flow Incorporating GraphSAGE, Hypergraph, Social-meaningful Edge Weights and Temporal Exploitation

Predicting metro passenger flow precisely is of great importance for dyn...

Heterogeneous Directed Hypergraph Neural Network over abstract syntax tree (AST) for Code Classification

Code classification is a difficult issue in program understanding and au...

Please sign up or login with your details

Forgot password? Click here to reset