Haoyi Xiong

Pareto Optimization for Active Learning under Out-of-Distribution Data Scenarios

2022 · arXiv (Cornell University)

Pool-based Active Learning (AL) has achieved great success in minimizing labeling cost by sequentially selecting informative unlabeled samples from a large unlabeled data pool and querying their labels from oracle/annotators. However, existing AL sampling strategies …

<i>MHRR</i>: MOOCs Recommender Service With Meta Hierarchical Reinforced Ranking

2023 · IEEE Transactions on Services Computing

The exponential growth of Massive Open Online Courses (MOOCs) surges the needs of advanced models for personalized Online Education Services (OES). Existing solutions successfully recommend MOOCs courses via deep learning models, they however generate weak …

SOLA-GCL: Subgraph-Oriented Learnable Augmentation Method for Graph Contrastive Learning

2025 · Proceedings of the AAAI Conference on Artificial Intelligence

Graph contrastive learning has emerged as a powerful technique for learning graph representations that are robust and discriminative. However, traditional approaches often neglect the critical role of subgraph structures, particularly the intra-subgraph characteristics and inter-subgraph …