Xiao Zhang

Introducing DRAIL – a Step Towards Declarative Deep Relational Learning

2016

We introduce DRAIL, a new declarative framework for specifying Deep Relational Models. Our framework separates structural considerations, which express domain knowledge, from the learning architecture to simplify the process of building complex structural models.

Deep Recurrent Convolutional Neural Network: Improving Performance For Speech Recognition

2016 · arXiv (Cornell University)

A deep learning approach has been widely applied in sequence modeling problems. In terms of automatic speech recognition (ASR), its performance has significantly been improved by increasing large speech corpus and deeper neural network. Especially, …

Learning One-hidden-layer ReLU Networks via Gradient Descent

2018 · arXiv (Cornell University)

We study the problem of learning one-hidden-layer neural networks with Rectified Linear Unit (ReLU) activation function, where the inputs are sampled from standard Gaussian distribution and the outputs are generated from a noisy teacher network. …

Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization

2020 · arXiv (Cornell University)

Training machine learning models that are robust against adversarial inputs poses seemingly insurmountable challenges. To better understand adversarial robustness, we consider the underlying problem of learning robust representations. We develop a notion of representation vulnerability …

Semi-Supervised Breast Histological Image Classification by Node-Attention Graph Transfer Network

2020 · IEEE Access

As a major cause of leading female death, breast cancer is often diagnosed by histological images which has been resolved by many deep learning methods with the assistance of large amounts of annotated data. However, …

DCAP

2021

User response prediction, which aims to predict the probability that a user will provide a predefined positive response in a given context such as clicking on an ad or purchasing an item, is crucial to …

A Collaborative Filtering Algorithm based on Entropy and Trust Optimized Neighbor Selection

2022 · 2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD)

The Collaborative filtering (CF) is an emerging technology that deals with overload problems by providing recommendations for products that users may be interested in. Neighbor selection is a key part of the recommendation process. The …

Fast Second-Order Online Kernel Learning Through Incremental Matrix Sketching and Decomposition

2024

Second-order Online Kernel Learning (OKL) has attracted considerable research interest due to its promising predictive performance in streaming environments. However, existing second-order OKL approaches suffer from at least quadratic time complexity with respect to the …

LS-TGNN: Long and Short-Term Temporal Graph Neural Network for Session-Based Recommendation

2025 · Proceedings of the AAAI Conference on Artificial Intelligence

Session-Based Recommendation (SBR) based on Graph Neural Networks (GNN) has become a new paradigm for recommender systems, and plays a fundamental role in e-commerce and other relevant domains. Existing graph aggregation methods primarily form node …

DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models

2025

Jianyu Liu, Hangyu Guo, Ranjie Duan, Xingyuan Bu, Yancheng He, Shilong Li, Hui Huang, Jiaheng Liu, Yucheng Wang, Chenchen Jing, Xingwei Qu, Xiao Zhang, Pei Wang, Yanan Wu, Jihao Gu, Yangguang Li, Jianke Zhu. Proceedings …

Assessing and enhancing the reliability of Chinese large language models in dental implantology

2025 · BMC Oral Health

BACKGROUND: This study aimed to evaluate the reliability of five representative Chinese large language models (LLMs) in dental implantology. It also explored effective strategies for model enhancement. METHODS: A dataset of 100 dental implant-related questions …

Decentralized Reward Allocation Mechanism with Sybil Resilience: The Case of Stake Pools

2025

Proof-of-Stake (PoS) is an energy-efficient consensus where proposer election based on validator stakes causes centralization, especially in stake pools. However, existing reward allocation mechanisms aim to address centralization but increase the risk of Sybil attacks. …

Medical Exam Question Answering with Large-scale Reading Comprehension

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

Reading and understanding text is one important component in computer aided diagnosis in clinical medicine, also being a major research problem in the field of NLP. In this work, we introduce a question-answering task called …