Zobrazeno 1 - 10
of 381
pro vyhledávání: '"Wu, Jiayun"'
Graph Neural Networks (GNNs) are widely used for node classification tasks but often fail to generalize when training and test nodes come from different distributions, limiting their practicality. To overcome this, recent approaches adopt invariant l
Externí odkaz:
http://arxiv.org/abs/2406.01066
We establish a new model-agnostic optimization framework for out-of-distribution generalization via multicalibration, a criterion that ensures a predictor is calibrated across a family of overlapping groups. Multicalibration is shown to be associated
Externí odkaz:
http://arxiv.org/abs/2406.00661
Machine learning models, while progressively advanced, rely heavily on the IID assumption, which is often unfulfilled in practice due to inevitable distribution shifts. This renders them susceptible and untrustworthy for deployment in risk-sensitive
Externí odkaz:
http://arxiv.org/abs/2403.01874
Autor:
Yuan, Bing, Jiang, Zhang, Lyu, Aobo, Wu, Jiayun, Wang, Zhipeng, Yang, Mingzhe, Liu, Kaiwei, Mou, Muyun, Cui, Peng
Emergence and causality are two fundamental concepts for understanding complex systems. They are interconnected. On one hand, emergence refers to the phenomenon where macroscopic properties cannot be solely attributed to the cause of individual prope
Externí odkaz:
http://arxiv.org/abs/2312.16815
Machine learning algorithms minimizing average risk are susceptible to distributional shifts. Distributionally Robust Optimization (DRO) addresses this issue by optimizing the worst-case risk within an uncertainty set. However, DRO suffers from over-
Externí odkaz:
http://arxiv.org/abs/2311.05054
Graph Representation Learning (GRL) is an influential methodology, enabling a more profound understanding of graph-structured data and aiding graph clustering, a critical task across various domains. The recent incursion of attention mechanisms, orig
Externí odkaz:
http://arxiv.org/abs/2306.11307
As an intrinsic and fundamental property of big data, data heterogeneity exists in a variety of real-world applications, such as precision medicine, autonomous driving, financial applications, etc. For machine learning algorithms, the ignorance of da
Externí odkaz:
http://arxiv.org/abs/2304.00305
Temporal networks are suitable for modeling complex evolving systems. It has a wide range of applications, such as social network analysis, recommender systems, and epidemiology. Recently, modeling such dynamic systems has drawn great attention in ma
Externí odkaz:
http://arxiv.org/abs/2211.06590
Enhancing the stability of machine learning algorithms under distributional shifts is at the heart of the Out-of-Distribution (OOD) Generalization problem. Derived from causal learning, recent works of invariant learning pursue strict invariance with
Externí odkaz:
http://arxiv.org/abs/2206.02990
Publikováno v:
In International Journal of Biological Macromolecules September 2024 276 Part 2