Yong Liu

Learning User Dependencies for Recommendation

2017

Social recommender systems exploit users' social relationships to improve recommendation accuracy. Intuitively, a user tends to trust different people regarding with different scenarios. Therefore, one main challenge of social recommendation is to exploit the most …

Learning Vector-valued Functions with Local Rademacher Complexity and Unlabeled Data

2019 · arXiv (Cornell University)

We consider a general family of problems of which the output space admits vector-valued structure, covering a broad family of important domains, e.g. multi-label learning and multi-class classification. By using local Rademacher complexity and unlabeled …

USV Target Interception Control With Reinforcement Learning and Motion Prediction Method

2022 · 2022 37th Youth Academic Annual Conference of Chinese Association of Automation (YAC)

In this paper, an unmanned surface vehicle (USV) target interception problem is studied with reinforcement learning (RL)-based method. In the proposed new structure, the proximal policy optimization (PPO) and proportional derivative (PD) are combined. First, …

Reliable Federated Disentangling Network for Non-IID Domain Feature

2023 · arXiv (Cornell University)

Federated learning (FL), as an effective decentralized distributed learning approach, enables multiple institutions to jointly train a model without sharing their local data. However, the domain feature shift caused by different acquisition devices/clients substantially degrades …

FedNS: A Fast Sketching Newton-Type Algorithm for Federated Learning

2024 · Proceedings of the AAAI Conference on Artificial Intelligence

Recent Newton-type federated learning algorithms have demonstrated linear convergence with respect to the communication rounds. However, communicating Hessian matrices is often unfeasible due to their quadratic communication complexity. In this paper, we introduce a novel …

An Aggregation-Free Federated Learning for Tackling Data Heterogeneity

2024 · arXiv (Cornell University)

The performance of Federated Learning (FL) hinges on the effectiveness of utilizing knowledge from distributed datasets. Traditional FL methods adopt an aggregate-then-adapt framework, where clients update local models based on a global model aggregated by …

MIT: A Multi-Tower Information Transfer Framework Based on Hierarchical Task Relationship Modeling

2025

With the advancement of e-commerce platforms and online recommendation systems, conversion objectives have evolved from singular to diverse goals. To simultaneously enhance the performance of multiple conversion objectives, multi-task learning has become a classic solution. …

The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Models

2025

Ensuring awareness of fairness and privacy in Large Language Models (LLMs) is critical.Interestingly, we discover a counterintuitive trade-off phenomenon that enhancing an LLM's privacy awareness through Supervised Fine-Tuning (SFT) methods significantly decreases its fairness awareness …

From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs

2025 · arXiv (Cornell University)

Memory is the process of encoding, storing, and retrieving information, allowing humans to retain experiences, knowledge, skills, and facts over time, and serving as the foundation for growth and effective interaction with the world. It …

Improved Recurrent Neural Networks for Session-based Recommendations

2016

Recurrent neural networks (RNNs) were recently proposed for the session-based recommendation task. The models showed promising improvements over traditional recommendation approaches. In this work, we further study RNN-based models for session-based recommendations. We propose the …