Výsledky vyhledávání

Report

Relation Also Knows: Rethinking the Recall and Editing of Factual Associations in Auto-Regressive Transformer Language Models

Autor: Liu, Xiyu, Liu, Zhengxiao, Gu, Naibin, Lin, Zheng, Ma, Wanli, Xiang, Ji, Wang, Weiping

The storage and recall of factual associations in auto-regressive transformer language models (LMs) have drawn a great deal of attention, inspiring knowledge editing by directly modifying the located model weights. Most editing works achieve knowledg

Externí odkaz: http://arxiv.org/abs/2408.15091

Zobrazit plný text záznamu

Report

Federated Hypergraph Learning: Hyperedge Completion with Local Differential Privacy

Autor: Luo, Linfeng, Tang, Fengxiao, Liu, Xiyu, Guo, Zhiqi, Qiu, Zihao, Zhao, Ming

As the volume and complexity increase, graph-structured data commonly need to be split and stored across distributed systems. To enable data mining on subgraphs within these distributed systems, federated graph learning has been proposed, allowing co

Externí odkaz: http://arxiv.org/abs/2408.05160

Zobrazit plný text záznamu

Report

Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning

Autor: Gu, Naibin, Fu, Peng, Liu, Xiyu, Shen, Bowen, Lin, Zheng, Wang, Weiping

Parameter-efficient fine-tuning (PEFT) has emerged as the predominant technique for fine-tuning in the era of large language models. However, existing PEFT methods still have inadequate training efficiency. Firstly, the utilization of large-scale fou

Externí odkaz: http://arxiv.org/abs/2406.03792

Zobrazit plný text záznamu

Report

Exotic Spin-dependent Energy-level Shift Noise Induced by Thermal Motion

Autor: Xiao, Wei, Liu, Xiyu, Wu, Teng, Peng, Xiang, Guo, Hong

Searching for exotic spin-dependent interactions that beyond the standard model has been of interest for past decades and is crucial for unraveling the mysteries of the universe. Previous laboratory searches primarily focus on searching for either st

Externí odkaz: http://arxiv.org/abs/2401.05862

Zobrazit plný text záznamu