Ds-agent: Automated data science by empowering large language models with case-based reasoning

S Guo, C Deng, Y Wen, H Chen, Y Chang… - arxiv preprint arxiv …, 2024‏ - arxiv.org
In this work, we investigate the potential of large language models (LLMs) based agents to
automate data science tasks, with the goal of comprehending task requirements, then …

Multi-track message passing: tackling oversmoothing and oversquashing in graph learning via preventing heterophily mixing

H Pei, Y Li, H Deng, J Hai, P Wang, J Ma… - … on Machine Learning, 2024‏ - openreview.net
The advancement toward deeper graph neural networks is currently obscured by two
inherent issues in message passing,* oversmoothing* and* oversquashing*. We identify the …

Positive and unlabeled learning with controlled probability boundary fence

C Li, Y Dai, L Feng, X Li, B Wang… - Forty-first International …, 2024‏ - openreview.net
Positive and Unlabeled (PU) learning refers to a special case of binary classification, and
technically, it aims to induce a binary classifier from a few labeled positive training instances …

GPFedRec: Graph-guided personalization for federated recommendation

C Zhang, G Long, T Zhou, Z Zhang, P Yan… - Proceedings of the 30th …, 2024‏ - dl.acm.org
The federated recommendation system is an emerging AI service architecture that provides
recommendation services in a privacy-preserving manner. Using user-relation graphs to …

Accurate PROTAC targeted degradation prediction with DegradeMaster

J Liu, M Roy, L Isbel, F Li - bioRxiv, 2025‏ - biorxiv.org
Motivation: Proteolysis-targeting chimeras (PROTACs) are heterobifunctional molecules that
can degrade" undruggable" protein of interest (POI) by recruiting E3 ligases and hijacking …

Semi-supervised Node Importance Estimation with Informative Distribution Modeling for Uncertainty Regularization

Y Chen, T Wang, Y Fang, Y **ao - THE WEB CONFERENCE 2025‏ - openreview.net
Graph node importance estimation, a classical problem in network analysis, underpins
various web applications. To improve estimation accuracy, previous methods either exploit …