Deep Structural Point Process for Learning Temporal Interaction Networks

1 code implementation • 8 Jul 2021 • Jiangxia Cao, Xixun Lin, Xin Cong, Shu Guo, Hengzhu Tang, Tingwen Liu, Bin Wang

A temporal interaction network consists of a series of chronological interactions between users and items.

Task-adaptive Neural Process for User Cold-Start Recommendation

1 code implementation • 26 Feb 2021 • Xixun Lin, Jia Wu, Chuan Zhou, Shirui Pan, Yanan Cao, Bin Wang

In this paper, we develop a novel meta-learning recommender called task-adaptive neural process (TaNP).

Meta-Learning Recommendation Systems

Bipartite Graph Embedding via Mutual Information Maximization

1 code implementation • 10 Dec 2020 • Jiangxia Cao, Xixun Lin, Shu Guo, Luchen Liu, Tingwen Liu, Bin Wang

However, the global properties of bipartite graph, including community structures of homogeneous nodes and long-range dependencies of heterogeneous nodes, are not well preserved.

Graph Embedding Link Prediction

Compositional Learning of Relation Path Embedding for Knowledge Base Completion

no code implementations • 22 Nov 2016 • Xixun Lin, Yanchun Liang, Fausto Giunchiglia, Xiaoyue Feng, Renchu Guan

In this paper, we study the problem of how to better embed entities and relations of knowledge bases into different low-dimensional spaces by taking full advantage of the additional semantics of relation paths, and we propose a compositional learning model of relation path embedding (RPE).

Knowledge Base Completion Relation