Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Huang, Zhengting"'
Autor:
Chen, Xuexin, Cai, Ruichu, Zheng, Kaitao, Jiang, Zhifan, Huang, Zhengting, Hao, Zhifeng, Li, Zijian
Graph Out-of-Distribution (OOD), requiring that models trained on biased data generalize to the unseen test data, has considerable real-world applications. One of the most mainstream methods is to extract the invariant subgraph by aligning the origin
Externí odkaz:
http://arxiv.org/abs/2407.15273
Addressing the challenge of high annotation costs in solving Math Word Problems (MWPs) through full supervision with intermediate equations, recent works have proposed weakly supervised task settings that rely solely on the final answer as a supervis
Externí odkaz:
http://arxiv.org/abs/2403.14390
Autor:
Chen, Xuexin, Cai, Ruichu, Zheng, Kaitao, Jiang, Zhifan, Huang, Zhengting, Hao, Zhifeng, Li, Zijian
Graph Out-of-Distribution (OOD), requiring that models trained on biased data generalize to the unseen test data, has a massive of real-world applications. One of the most mainstream methods is to extract the invariant subgraph by aligning the origin
Externí odkaz:
http://arxiv.org/abs/2402.09165
Autor:
Chen, Xuexin, Cai, Ruichu, Huang, Zhengting, Zhu, Yuxuan, Horwood, Julien, Hao, Zhifeng, Li, Zijian, Hernandez-Lobato, Jose Miguel
We investigate the problem of explainability for machine learning models, focusing on Feature Attribution Methods (FAMs) that evaluate feature importance through perturbation tests. Despite their utility, FAMs struggle to distinguish the contribution
Externí odkaz:
http://arxiv.org/abs/2402.08845