Ming Zhang

Global Perspectives on the Role of Two-Year/Technical/Junior Colleges in Computing Education

2016

This panel presents varying global perspectives on the role of community colleges and 2- or 3-year technical schools (collectively called junior colleges here) in computing education. In some countries, students interested in a career in …

Robust stabilization of uncertain quantum open systems

2017

We exploit how to overcome phase damping decoherence when the phase damping parameters are uncertain. It is shown that the “relaxed” control goal may be achieved by combing simple open-loop coherent control with periodic projective …

An Ensemble of Retrieval-Based and Generation-Based Human-Computer Conversation Systems

2018

Human-computer conversation systems have attracted much attention in Natural Language Processing. Conversation systems can be roughly divided into two categories: retrieval-based and generation-based systems. Retrieval systems search a user-issued utterance (namely a query ) in …

Early Prediction of Sepsis From Clinical Data via Heterogeneous Event Aggregation

2019 · Computing in cardiology

Sepsis is a life-threatening condition that seriously endangers millions of people over the world. Hopefully, with the widespread availability of electronic health records (EHR), predictive models that can effectively deal with clinical sequential data increase …

TGNN: A Joint Semi-supervised Framework for Graph-level Classification

2022

This paper studies semi-supervised graph classification, a crucial task with a wide range of applications in social network analysis and bioinformatics. Recent works typically adopt graph neural networks to learn graph-level representations for classification, failing …

Learning on Graphs under Label Noise

2023

Node classification on graphs is a significant task with a wide range of applications, including social analysis and anomaly detection. Even though graph neural networks (GNNs) have produced promising results on this task, current techniques …

DisCo: Graph-Based Disentangled Contrastive Learning for Cold-Start Cross-Domain Recommendation

2024 · arXiv (Cornell University)

Recommender systems are widely used in various real-world applications, but they often encounter the persistent challenge of the user cold-start problem. Cross-domain recommendation (CDR), which leverages user interactions from one domain to improve prediction performance …

AutoInt

2019

Click-through rate (CTR) prediction, which aims to predict the probability of a user clicking on an ad or an item, is critical to many online applications such as online advertising and recommender systems. The problem …

Session-Based Social Recommendation via Dynamic Graph Attention Networks

2019

Online communities such as Facebook and Twitter are enormously popular and have become an essential part of the daily life of many of their users. Through these platforms, users can discover and create information that …