9 papers
When Recommendation Denoising Meets Popularity Bias: Understanding and Mitigating Their Interaction
Guohang Zeng, Jie Lu, Guangquan Zhang
Implicit feedback is the dominant data source for recommender systems, but behavioral logs are often contaminated by false-positive interactions caused by mis-clicks, biased exposu…
On the Provable Importance of Gradients for Language-Assisted Image Clustering
Bo Peng, Jie Lu, Guangquan Zhang +1
This paper investigates the recently emerged problem of Language-assisted Image Clustering (LaIC), where textual semantics are leveraged to improve the discriminability of visual r…
TPA: Next Token Probability Attribution for Detecting Hallucinations in RAG
Pengqian Lu, Jie Lu, Anjin Liu +1
Detecting hallucinations in Retrieval-Augmented Generation remains a challenge. Prior approaches attribute hallucinations to a binary conflict between internal knowledge stored in…
Generalized Incremental Learning under Concept Drift across Evolving Data Streams
En Yu, Jie Lu, Guangquan Zhang
Real-world data streams exhibit inherent non-stationarity characterized by concept drift, posing significant challenges for adaptive learning systems. While existing methods addres…
Autonomous Source Knowledge Selection in Multi-Domain Adaptation
Keqiuyin Li, Jie Lu, Hua Zuo +1
Unsupervised multi-domain adaptation plays a key role in transfer learning by leveraging acquired rich source information from multiple source domains to solve target task from an…
Privacy-Utility Trade-off in Data Publication: A Bilevel Optimization Framework with Curvature-Guided Perturbation
Yi Yin, Guangquan Zhang, Hua Zuo +1
Machine learning models require datasets for effective training, but directly sharing raw data poses significant privacy risk such as membership inference attacks (MIA). To mitigat…