Deep Iterative and Adaptive Learning for Graph Neural Networks

Abstract

In this paper, we propose an end-to-end graph learning framework, namely Deep Iterative and Adaptive Learning for Graph Neural Networks (DIAL-GNN), for jointly learning the graph structure and graph embeddings simultaneously. We first cast the graph structure learning problem as a similarity metric learning problem and leverage an adapted graph regularization for controlling smoothness, connectivity and sparsity of the generated graph. We further propose a novel iterative method for searching for a hidden graph structure that augments the initial graph structure. Our iterative method dynamically stops when the learned graph structure approaches close enough to the optimal graph. Our extensive experiments demonstrate that the proposed DIAL-GNN model can consistently outperform or match state-of-the-art baselines in terms of both downstream task performance and computational time. The proposed approach can cope with both transductive learning and inductive learning.

6 pages. Accepted at the AAAI 2020 Workshop on Deep Learning on Graphs: Methodologies and Applications (AAAI DLGMA 2020). Final Version

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Semi-Supervised Classification with Graph Convolutional Networks
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Inductive Representation Learning on Large Graphs
• Learning Discrete Structures for Graph Neural Networks
• Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
• Learning Conditioned Graph Structures for Interpretable Visual Question Answering
• Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions
• Large Scale Graph Learning from Smooth Signals
• GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension
• Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model
• SQL-to-Text Generation with Graph-to-Sequence Model

Cited by in corpus (8)

• Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters
• Revisiting Over-smoothing in Deep GCNs
• SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks
• GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension
• Kernel-based Graph Learning from Smooth Signals: A Functional Viewpoint
• Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks
• Learning Chebyshev Basis in Graph Convolutional Networks for Skeleton-based Action Recognition
• Deep graph learning for semi-supervised classification