Jianxin Li

DPS: A DSM-based Parameter Server for Machine Learning

2017

To solve the problem of efficient storing and updating of model parameters in the learning process, the parameter server is concerned as a high-throughput distributed machine learning (ML) architecture with the emergence of big models …

Interpretable and Efficient Heterogeneous Graph Convolutional Network

2021 · IEEE Transactions on Knowledge and Data Engineering

Graph Convolutional Network (GCN) has achieved extraordinary success in learning representations of nodes in graphs. However, regarding Heterogeneous Information Network (HIN), existing HIN-oriented GCN methods still suffer from two deficiencies: (1) they cannot flexibly explore …

Triplet Attention

2021

The Transformer model has benefited various real-world applications, where the self-attention mechanism with dot-products shows superior alignment ability on building long dependency. However, the pair-wisely attended self-attention limits further performance improvement on challenging tasks. To …

RoSearch: Search for Robust Student Architectures When Distilling Pre-trained Language Models

2021 · arXiv (Cornell University)

Pre-trained language models achieve outstanding performance in NLP tasks. Various knowledge distillation methods have been proposed to reduce the heavy computation and storage requirements of pre-trained language models. However, from our observations, student models acquired …

Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relations

2021 · arXiv (Cornell University)

Event extraction is a fundamental task for natural language processing. Finding the roles of event arguments like event participants is essential for event extraction. However, doing so for real-life event descriptions is challenging because an …

Recommendation model based on intention decomposition and heterogeneous information fusion

2023 · Mathematical Biosciences & Engineering

In order to solve the problem of timeliness of user and item interaction intention and the noise caused by heterogeneous information fusion, a recommendation model based on intention decomposition and heterogeneous information fusion (IDHIF) is …

Self-supervised Bipartite Graph Representation Learning: A Dirichlet Max-margin Matrix Factorization Approach

2024 · ACM Transactions on Intelligent Systems and Technology

Bipartite graph representation learning aims to obtain node embeddings by compressing sparse vectorized representations of interactions between two types of nodes, e.g., users and items. Incorporating structural attributes among homogeneous nodes, such as user communities, …

Session-Oriented Fairness-Aware Recommendation via Dual Temporal Convolutional Networks

2024 · IEEE Transactions on Knowledge and Data Engineering

Session-based Recommender Systems (SBRSs) aim at timely predicting the next likely item by capturing users’ current preferences in sessions. Existing SBRSs research only focuses on maximizing session utilities, and little has been done on the …

Evolving Graph Learning for Out-of-Distribution Generalization in Non-Stationary Environments

2025 · IEEE Transactions on Pattern Analysis and Machine Intelligence

Graph neural networks have shown remarkable success in exploiting the spatial and temporal patterns on dynamic graphs. However, existing GNNs exhibit poor generalization ability under distribution shifts, which is inevitable in dynamic scenarios. As dynamic …