Embedding learning is essential in various research areas, especially natural language processing (NLP). However, given the nature of unstructured data and word frequency distribution, general pre-trained embeddings, such as word2vec GloVe, are often inferior tasks for specific domains because missing or unreliable embedding. In many domain-specific tasks, pre-existing side information can be c...

Network data has attracted tremendous attention in recent years, and most conventional networks focus on pairwise interactions between two vertices. However, real-life network may display more complex structures, multi-way among vertices arise naturally. In this article, we propose a novel method for detecting community structure general hypergraph networks, uniform or non-uniform. The proposed...

We present Graph Attention Collaborative Similarity Embedding (GACSE), a new recommendation framework that exploits collaborative information in the user-item bipartite graph for representation learning. Our consists of two parts: first part is to learn explicit filtering such as association through embedding propagation with attention mechanism, and second implicit user-user similarities item-...

Structure Preserving Embedding (SPE) is a method for embedding graphs in lowdimensional Euclidean space such that the embedding preserves the graph’s global topological properties. Specifically, topology is preserved if a connectivity algorithm can recover the original graph from only the coordinates of its nodes after embedding. Given an input graph and an algorithm for linking embedded nodes,...

A graph is planar if it can be drawn on the plane with no crossing edges. There are several linear time planar embedding algorithms but all are considered by many to be quite complicated. This paper presents a new method for performing linear time planar graph embedding which avoids some of the complexities of previous approaches (including the need to rst st-number the vertices). Our new algor...