Yongdong Zhang

Attribute-Induced Bias Eliminating for Transductive Zero-Shot Learning

2021 · IEEE Transactions on Multimedia

Transductive zero-shot learning is designed to recognize unseen categories by aligning both visual and semantic information in a joint embedding space. Four types of domain biases exist in Transductive ZSL,i.e.,visual biasandsemantic biasin two domains, and …

How to Retrain Recommender System?

2020

Practical recommender systems need be periodically retrained to refresh the model with new interaction data. To pursue high model fidelity, it is usually desirable to retrain the model on both historical and new data, since …

Prototype-Augmented Self-Supervised Generative Network for Generalized Zero-Shot Learning

2024 · IEEE Transactions on Image Processing

Generalized Zero-Shot Learning (GZSL) aims at recognizing images from both seen and unseen classes by constructing correspondences between visual images and semantic embedding. However, existing methods suffer from a strong bias problem, where unseen images …

UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language Models

2025 · arXiv (Cornell University)

Large Language Models (LLMs) have achieved remarkable progress across a wide range of tasks, but remain vulnerable to safety risks such as harmful content generation and jailbreak attacks. Existing safety techniques -- including external guardrails, …

DACL-RAG: Data Augmentation Strategy with Curriculum Learning for Retrieval-Augmented Generation

2025 · arXiv (Cornell University)

Retrieval-Augmented Generation (RAG) is an effective method to enhance the capabilities of large language models (LLMs). Existing methods typically optimize the retriever or the generator in a RAG system by directly using the top-k retrieved …

Relational Collaborative Filtering

2019

Existing item-based collaborative filtering (ICF) methods leverage only the relation of collaborative similarity - i.e., the item similarity evidenced by user interactions like ratings and purchases. Nevertheless, there exist multiple relations between items in real-world …

LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation

2020 · arXiv (Cornell University)

Graph Convolution Network (GCN) has become new state-of-the-art for collaborative filtering. Nevertheless, the reasons of its effectiveness for recommendation are not well understood. Existing work that adapts GCN to recommendation lacks thorough ablation analyses on …

Curriculum Learning for Natural Language Understanding

2020

With the great success of pre-trained language models, the pretrain-finetune paradigm now becomes the undoubtedly dominant solution for natural language understanding (NLU) tasks. At the fine-tune stage, target task data is usually introduced in a …

LightGCN

2020

Graph Convolution Network (GCN) has become new state-of-the-art for collaborative filtering. Nevertheless, the reasons of its effectiveness for recommendation are not well understood. Existing work that adapts GCN to recommendation lacks thorough ablation analyses on …

Causal Intervention for Leveraging Popularity Bias in Recommendation

2021

Recommender system usually faces popularity bias issues: from the data perspective, items exhibit uneven (usually long-tail) distribution on the interaction frequency; from the method perspective, collaborative filtering methods are prone to amplify the bias by …