Zobrazeno 1 - 10
of 178
pro vyhledávání: '"SUN Zequn"'
Autor:
CHEN Junhong, WU Yi, WANG Yingqiao, LI Weibin, CHEN Yuhong, WANG Yali, ZHANG Xiaopeng, ZHENG Xue, ZHANG Chunguang, XUAN Weimin, YAO Lieying, TAN Hao, LUO Wenwu, ZHOU Peihai, SONG Xianming, LIU Shaoxuan, SUN Zequn, CONG Zijian, YANG Enwu, GE Xingxin, GAO Xiang
Publikováno v:
He jishu, Vol 47, Iss 5, Pp 050013-050013 (2024)
BackgroundENN Science and Technology Development Co., Ltd. (ENN Fusion Technology R&D Center) is upgrading its compact fusion research facility EXL-50 to EXL-50U. Both devices are the conventional conductor tokamak, on which the magnet power supply s
Externí odkaz:
https://doaj.org/article/8eeb66772555436e90de4dd624ddcbaf
Extensive knowledge graphs (KGs) have been constructed to facilitate knowledge-driven tasks across various scenarios. However, existing work usually develops separate reasoning models for different KGs, lacking the ability to generalize and transfer
Externí odkaz:
http://arxiv.org/abs/2410.12288
Traditional knowledge graph (KG) completion models learn embeddings to predict missing facts. Recent works attempt to complete KGs in a text-generation manner with large language models (LLMs). However, they need to ground the output of LLMs to KG en
Externí odkaz:
http://arxiv.org/abs/2407.16127
Parameter-efficient finetuning (PEFT) is a key technique for adapting large language models (LLMs) to downstream tasks. In this paper, we study leveraging knowledge graph embeddings to improve the effectiveness of PEFT. We propose a knowledgeable ada
Externí odkaz:
http://arxiv.org/abs/2403.14950
Entity alignment (EA) seeks identical entities in different knowledge graphs, which is a long-standing task in the database research. Recent work leverages deep learning to embed entities in vector space and align them via nearest neighbor search. Al
Externí odkaz:
http://arxiv.org/abs/2312.04877
In this paper, we present the ``joint pre-training and local re-training'' framework for learning and applying multi-source knowledge graph (KG) embeddings. We are motivated by the fact that different KGs contain complementary information to improve
Externí odkaz:
http://arxiv.org/abs/2306.02679
Joint representation learning over multi-sourced knowledge graphs (KGs) yields transferable and expressive embeddings that improve downstream tasks. Entity alignment (EA) is a critical step in this process. Despite recent considerable research progre
Externí odkaz:
http://arxiv.org/abs/2306.02622
Autor:
Guo, Lingbing, Wang, Weiqing, Chen, Zhuo, Zhang, Ningyu, Sun, Zequn, Lai, Yixuan, Zhang, Qiang, Chen, Huajun
Reasoning system dynamics is one of the most important analytical approaches for many scientific studies. With the initial state of a system as input, the recent graph neural networks (GNNs)-based methods are capable of predicting the future state di
Externí odkaz:
http://arxiv.org/abs/2305.14642
Knowledge graphs (KGs) store rich facts about the real world. In this paper, we study KG alignment, which aims to find alignment between not only entities but also relations and classes in different KGs. Alignment at the entity level can cross-fertil
Externí odkaz:
http://arxiv.org/abs/2304.04389
Existing knowledge graph (KG) embedding models have primarily focused on static KGs. However, real-world KGs do not remain static, but rather evolve and grow in tandem with the development of KG applications. Consequently, new facts and previously un
Externí odkaz:
http://arxiv.org/abs/2211.15845