BaGFN: Broad attentive graph fusion network for high-order feature interactions

Zhifeng Xie, Wenling Zhang, Bin Sheng, Ping Li, C. L. Philip Chen

Research output: Journal article publicationJournal articleAcademic researchpeer-review

105 Citations (Scopus)

Abstract

Modeling feature interactions is of crucial significance to high-quality feature engineering on multifiled sparse data. At present, a series of state-of-the-art methods extract cross features in a rather implicit bitwise fashion and lack enough comprehensive and flexible competence of learning sophisticated interactions among different feature fields. In this article, we propose a new broad attentive graph fusion network (BaGFN) to better model high-order feature interactions in a flexible and explicit manner. On the one hand, we design an attentive graph fusion module to strengthen high-order feature representation under graph structure. The graph-based module develops a new bilinear-cross aggregation function to aggregate the graph node information, employs the self-attention mechanism to learn the impact of neighborhood nodes, and updates the high-order representation of features by multihop fusion steps. On the other hand, we further construct a broad attentive cross module to refine high-order feature interactions at a bitwise level. The optimized module designs a new broad attention mechanism to dynamically learn the importance weights of cross features and efficiently conduct the sophisticated high-order feature interactions at the granularity of feature dimensions. The final experimental results demonstrate the effectiveness of our proposed model.

Original languageEnglish
Pages (from-to)1-15
Number of pages15
JournalIEEE Transactions on Neural Networks and Learning Systems
DOIs
Publication statusAccepted/In press - Oct 2021

Keywords

  • Aggregates
  • Attention mechanism
  • broad learning system (BLS)
  • Data models
  • Feature extraction
  • feature interactions
  • Frequency modulation
  • graph neural networks.
  • Learning systems
  • Predictive models
  • Transforms

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'BaGFN: Broad attentive graph fusion network for high-order feature interactions'. Together they form a unique fingerprint.

Cite this