activity
20192024
most citedMultimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations

167 citations · 252 across the 8 of their papers we have counts for

collaborators

10 papers

cs.LG20241 cited

Meta-Learn Unimodal Signals with Weak Supervision for Multimodal Sentiment Analysis

Sijie Mai, Yu Zhao, Ying Zeng +2

Multimodal sentiment analysis aims to effectively integrate information from various sources to infer sentiment, where in many cases there are no annotations for unimodal labels. T…

cs.LG20223 cited

Relation-dependent Contrastive Learning with Cluster Sampling for Inductive Relation Prediction

Jianfeng Wu, Sijie Mai, Haifeng Hu

Relation prediction is a task designed for knowledge graph completion which aims to predict missing relationships between entities. Recent subgraph-based models for inductive relat…

cs.LG2022167 cited

Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations

Sijie Mai, Ying Zeng, Haifeng Hu

Learning effective joint embedding for cross-modal data has always been a focus in the field of multimodal machine learning. We argue that during multimodal fusion, the generated m…

cs.LG20223 cited

Communicative Subgraph Representation Learning for Multi-Relational Inductive Drug-Gene Interaction Prediction

Jiahua Rao, Shuangjia Zheng, Sijie Mai +1

Illuminating the interconnections between drugs and genes is an important topic in drug development and precision medicine. Currently, computational predictions of drug-gene intera…

cs.AI202113 cited

Hybrid Contrastive Learning of Tri-Modal Representation for Multimodal Sentiment Analysis

Sijie Mai, Ying Zeng, Shuangjia Zheng +1

The wide application of smart devices enables the availability of multimodal data, which can be utilized in many tasks. In the field of multimodal sentiment analysis (MSA), most pr…

cs.CL202137 cited

Graph Capsule Aggregation for Unaligned Multimodal Sequences

Jianfeng Wu, Sijie Mai, Haifeng Hu

Humans express their opinions and emotions through multiple modalities which mainly consist of textual, acoustic and visual modalities. Prior works on multimodal sentiment analysis…