Zobrazeno 1 - 10
of 329
pro vyhledávání: '"SONG, Guojie"'
Human values and their measurement are long-standing interdisciplinary inquiry. Recent advances in AI have sparked renewed interest in this area, with large language models (LLMs) emerging as both tools and subjects of value measurement. This work in
Externí odkaz:
http://arxiv.org/abs/2409.12106
Large Language Models (LLMs) are transforming diverse fields and gaining increasing influence as human proxies. This development underscores the urgent need for evaluating value orientations and understanding of LLMs to ensure their responsible integ
Externí odkaz:
http://arxiv.org/abs/2406.04214
Placement is a critical and challenging step of modern chip design, with routability being an essential indicator of placement quality. Current routability-oriented placers typically apply an iterative two-stage approach, wherein the first stage gene
Externí odkaz:
http://arxiv.org/abs/2406.02651
Graph Transformers (GTs) have significantly advanced the field of graph representation learning by overcoming the limitations of message-passing graph neural networks (GNNs) and demonstrating promising performance and expressive power. However, the q
Externí odkaz:
http://arxiv.org/abs/2405.03481
Autor:
Ye, Haoran, Wang, Jiarui, Cao, Zhiguang, Berto, Federico, Hua, Chuanbo, Kim, Haeyeon, Park, Jinkyoo, Song, Guojie
The omnipresence of NP-hard combinatorial optimization problems (COPs) compels domain experts to engage in trial-and-error heuristic design. The long-standing endeavor of design automation has gained new momentum with the rise of large language model
Externí odkaz:
http://arxiv.org/abs/2402.01145
Autor:
Berto, Federico, Hua, Chuanbo, Park, Junyoung, Luttmann, Laurin, Ma, Yining, Bu, Fanchen, Wang, Jiarui, Ye, Haoran, Kim, Minsu, Choi, Sanghyeok, Zepeda, Nayeli Gast, Hottung, André, Zhou, Jianan, Bi, Jieyi, Hu, Yu, Liu, Fei, Kim, Hyeonah, Son, Jiwoo, Kim, Haeyeon, Angioni, Davide, Kool, Wouter, Cao, Zhiguang, Zhang, Qingfu, Kim, Joungho, Zhang, Jie, Shin, Kijung, Wu, Cathy, Ahn, Sungsoo, Song, Guojie, Kwon, Changhyun, Tierney, Kevin, Xie, Lin, Park, Jinkyoo
Deep reinforcement learning (RL) has recently shown significant benefits in solving combinatorial optimization (CO) problems, reducing reliance on domain expertise, and improving computational efficiency. However, the field lacks a unified benchmark
Externí odkaz:
http://arxiv.org/abs/2306.17100
Graph Transformer has recently received wide attention in the research community with its outstanding performance, yet its structural expressive power has not been well analyzed. Inspired by the connections between Weisfeiler-Lehman (WL) graph isomor
Externí odkaz:
http://arxiv.org/abs/2305.13987
Autor:
Zhang, Peiyan, Yan, Yuchen, Li, Chaozhuo, Wang, Senzhang, Xie, Xing, Song, Guojie, Kim, Sunghun
Many real-world graph learning tasks require handling dynamic graphs where new nodes and edges emerge. Dynamic graph learning methods commonly suffer from the catastrophic forgetting problem, where knowledge learned for previous graphs is overwritten
Externí odkaz:
http://arxiv.org/abs/2305.13825
Autor:
Jin, Di, Wang, Luzhi, Zheng, Yizhen, Song, Guojie, Jiang, Fei, Li, Xiang, Lin, Wei, Pan, Shirui
Recommender systems are essential to various fields, e.g., e-commerce, e-learning, and streaming media. At present, graph neural networks (GNNs) for session-based recommendations normally can only recommend items existing in users' historical session
Externí odkaz:
http://arxiv.org/abs/2305.05848
Graph Transformer is gaining increasing attention in the field of machine learning and has demonstrated state-of-the-art performance on benchmarks for graph representation learning. However, as current implementations of Graph Transformer primarily f
Externí odkaz:
http://arxiv.org/abs/2305.02866