Zobrazeno 1 - 10
of 114
pro vyhledávání: '"Bian, Yatao"'
Recently there has been a surge of interest in extending the success of large language models (LLMs) to graph modality, such as social networks and molecules. As LLMs are predominantly trained with 1D text data, most existing approaches adopt a graph
Externí odkaz:
http://arxiv.org/abs/2406.14021
Recent studies have highlighted fairness issues in Graph Neural Networks (GNNs), where they produce discriminatory predictions against specific protected groups categorized by sensitive attributes such as race and age. While various efforts to enhanc
Externí odkaz:
http://arxiv.org/abs/2406.13544
Interpretable graph neural networks (XGNNs ) are widely adopted in various scientific applications involving graph-structured data. Existing XGNNs predominantly adopt the attention-based mechanism to learn edge or node importance for extracting and m
Externí odkaz:
http://arxiv.org/abs/2406.07955
Message passing mechanism contributes to the success of GNNs in various applications, but also brings the oversquashing problem. Recent works combat oversquashing by improving the graph spectrums with rewiring techniques, disrupting the structural bi
Externí odkaz:
http://arxiv.org/abs/2403.11199
Autor:
Wang, Haoyu, Ma, Guozheng, Meng, Ziqiao, Qin, Zeyu, Shen, Li, Zhang, Zhong, Wu, Bingzhe, Liu, Liu, Bian, Yatao, Xu, Tingyang, Wang, Xueqian, Zhao, Peilin
Self-alignment is an effective way to reduce the cost of human annotation while ensuring promising model capability. However, most current methods complete the data collection and training steps in a single round, which may overlook the continuously
Externí odkaz:
http://arxiv.org/abs/2402.07610
Autor:
Xie, Binghui, Bian, Yatao, zhou, Kaiwen, Chen, Yongqiang, Zhao, Peilin, Han, Bo, Meng, Wei, Cheng, James
Learning neural subset selection tasks, such as compound selection in AI-aided drug discovery, have become increasingly pivotal across diverse applications. The existing methodologies in the field primarily concentrate on constructing models that cap
Externí odkaz:
http://arxiv.org/abs/2402.03139
Autor:
Qu, Youzhi, Wei, Chen, Du, Penghui, Che, Wenxin, Zhang, Chi, Ouyang, Wanli, Bian, Yatao, Xu, Feiyang, Hu, Bin, Du, Kai, Wu, Haiyan, Liu, Jia, Liu, Quanying
During the evolution of large models, performance evaluation is necessarily performed to assess their capabilities and ensure safety before practical application. However, current model evaluations mainly rely on specific tasks and datasets, lacking
Externí odkaz:
http://arxiv.org/abs/2402.02547
Graph contrastive learning (GCL) has emerged as a representative paradigm in graph self-supervised learning, where negative samples are commonly regarded as the key to preventing model collapse and producing distinguishable representations. Recent st
Externí odkaz:
http://arxiv.org/abs/2312.02619
Text watermarking has emerged as a pivotal technique for identifying machine-generated text. However, existing methods often rely on arbitrary vocabulary partitioning during decoding to embed watermarks, which compromises the availability of suitable
Externí odkaz:
http://arxiv.org/abs/2311.09832
Invariant graph representation learning aims to learn the invariance among data from different environments for out-of-distribution generalization on graphs. As the graph environment partitions are usually expensive to obtain, augmenting the environm
Externí odkaz:
http://arxiv.org/abs/2310.19035