Predicting the Silent Majority on Graphs: Knowledge Transferable Graph Neural Network

Abstract

Graphs consisting of vocal nodes ("the vocal minority") and silent nodes ("the silent majority"), namely VS-Graph, are ubiquitous in the real world. The vocal nodes tend to have abundant features and labels. In contrast, silent nodes only have incomplete features and rare labels, e.g., the description and political tendency of politicians (vocal) are abundant while not for ordinary people (silent) on the twitter's social network. Predicting the silent majority remains a crucial yet challenging problem. However, most existing message-passing based GNNs assume that all nodes belong to the same domain, without considering the missing features and distribution-shift between domains, leading to poor ability to deal with VS-Graph. To combat the above challenges, we propose Knowledge Transferable Graph Neural Network (KT-GNN), which models distribution shifts during message passing and representation learning by transferring knowledge from vocal nodes to silent nodes. Specifically, we design the domain-adapted "feature completion and message passing mechanism" for node representation learning while preserving domain difference. And a knowledge transferable classifier based on KL-divergence is followed. Comprehensive experiments on real-world scenarios (i.e., company financial risk assessment and political elections) demonstrate the superior performance of our method. Our source code has been open sourced.

Paper was accepted by WWW2023

References in corpus (14)

• GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
• Towards Deeper Graph Neural Networks
• Learning Multi-granularity User Intent Unit for Session-based Recommendation
• Factorizable Graph Convolutional Networks
• TabularNet: A Neural Network Architecture for Understanding Semantic Structures of Tabular Data
• TIMME: Twitter Ideology-detection via Multi-task Multi-relational Embedding
• A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal
• Evolutionary Preference Learning via Graph Nested GRU ODE for Session-based Recommendation
• Company-as-Tribe: Company Financial Risk Assessment on Tribe-Style Graph with Hierarchical Graph Neural Networks
• Characterizing networks of propaganda on Twitter: a case study
• Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration
• Distinguishing manipulated stocks via trading network analysis
• Learning on Graphs with Out-of-Distribution Nodes
• Neuron Campaign for Initialization Guided by Information Bottleneck Theory

Cited by in corpus (5)

• GraphGLOW: Universal and Generalizable Structure Learning for Graph Neural Networks
• Bridged-GNN: Knowledge Bridge Learning for Effective Knowledge Transfer
• Negative as Positive: Enhancing Out-of-distribution Generalization for Graph Contrastive Learning
• UniPoll: A Unified Social Media Poll Generation Framework via Multi-Objective Optimization
• LinkThief: Combining Generalized Structure Knowledge with Node Similarity for Link Stealing Attack against GNN