Zobrazeno 1 - 10
of 1 388
pro vyhledávání: '"Cao, Jiannong"'
Explainable molecular property prediction is essential for various scientific fields, such as drug discovery and material science. Despite delivering intrinsic explainability, linear models struggle with capturing complex, non-linear patterns. Large
Externí odkaz:
http://arxiv.org/abs/2410.08829
Blockchain oracle is a critical third-party web service for Decentralized Finance (DeFi) protocols. Oracles retrieve external information such as token prices from exchanges and feed them as trusted data sources into smart contracts, enabling core De
Externí odkaz:
http://arxiv.org/abs/2410.07893
Entity alignment (EA) aims to merge two knowledge graphs (KGs) by identifying equivalent entity pairs. Existing methods can be categorized into symbolic and neural models. Symbolic models, while precise, struggle with substructure heterogeneity and s
Externí odkaz:
http://arxiv.org/abs/2410.04153
Inductive spatial temporal prediction can generalize historical data to predict unseen data, crucial for highly dynamic scenarios (e.g., traffic systems, stock markets). However, external events (e.g., urban structural growth, market crash) and emerg
Externí odkaz:
http://arxiv.org/abs/2409.13253
In continual learning (CL), model growth enhances adaptability over new data, improving knowledge retention for more tasks. However, improper model growth can lead to severe degradation of previously learned knowledge, an issue we name as growth-indu
Externí odkaz:
http://arxiv.org/abs/2408.10566
Autor:
Zhang, Tianyi, Zhang, Wengyu, Zhang, Xulu, Wu, Jiaxin, Wei, Xiao-Yong, Cao, Jiannong, Li, Qing
Accurate human localization is crucial for various applications, especially in the Metaverse era. Existing high precision solutions rely on expensive, tag-dependent hardware, while vision-based methods offer a cheaper, tag-free alternative. However,
Externí odkaz:
http://arxiv.org/abs/2407.20870
The Diversity Bonus: Learning from Dissimilar Distributed Clients in Personalized Federated Learning
Autor:
Wu, Xinghao, Liu, Xuefeng, Niu, Jianwei, Zhu, Guogang, Tang, Shaojie, Li, Xiaotian, Cao, Jiannong
Personalized Federated Learning (PFL) is a commonly used framework that allows clients to collaboratively train their personalized models. PFL is particularly useful for handling situations where data from different clients are not independent and id
Externí odkaz:
http://arxiv.org/abs/2407.15464
Autor:
Liu, Zengding, Chen, Chen, Cao, Jiannong, Pan, Minglei, Liu, Jikui, Li, Nan, Miao, Fen, Li, Ye
Large language models (LLMs) have captured significant interest from both academia and industry due to their impressive performance across various textual tasks. However, the potential of LLMs to analyze physiological time-series data remains an emer
Externí odkaz:
http://arxiv.org/abs/2406.18069
As large language models (LLMs) appear to behave increasingly human-like in text-based interactions, more and more researchers become interested in investigating personality in LLMs. However, the diversity of psychological personality research and th
Externí odkaz:
http://arxiv.org/abs/2406.17624
Recent studies successfully learned static graph embeddings that are structurally fair by preventing the effectiveness disparity of high- and low-degree vertex groups in downstream graph mining tasks. However, achieving structure fairness in dynamic
Externí odkaz:
http://arxiv.org/abs/2406.13201