Zobrazeno 1 - 10
of 1 176
pro vyhledávání: '"LIU, XIAORUI"'
Research on long non-coding RNAs (lncRNAs) has garnered significant attention due to their critical roles in gene regulation and disease mechanisms. However, the complexity and diversity of lncRNA sequences, along with the limited knowledge of their
Externí odkaz:
http://arxiv.org/abs/2411.03522
Implicit models such as Deep Equilibrium Models (DEQs) have emerged as promising alternative approaches for building deep neural networks. Their certified robustness has gained increasing research attention due to security concerns. Existing certifie
Externí odkaz:
http://arxiv.org/abs/2411.00899
Transformer-based architectures have dominated various areas of machine learning in recent years. In this paper, we introduce a novel robust attention mechanism designed to enhance the resilience of transformer-based architectures. Crucially, this te
Externí odkaz:
http://arxiv.org/abs/2410.23182
Graph neural networks (GNNs) have demonstrated remarkable success in graph representation learning, and various sampling approaches have been proposed to scale GNNs to applications with large-scale graphs. A class of promising GNN training algorithms
Externí odkaz:
http://arxiv.org/abs/2410.05416
This work tackles an intriguing and fundamental open challenge in representation learning: Given a well-trained deep learning model, can it be reprogrammed to enhance its robustness against adversarial or noisy input perturbations without altering it
Externí odkaz:
http://arxiv.org/abs/2410.04577
Autor:
Fan, Wenqi, Wang, Shijie, Huang, Jiani, Chen, Zhikai, Song, Yu, Tang, Wenzhuo, Mao, Haitao, Liu, Hui, Liu, Xiaorui, Yin, Dawei, Li, Qing
Graphs play an important role in representing complex relationships in various domains like social networks, knowledge graphs, and molecular discovery. With the advent of deep learning, Graph Neural Networks (GNNs) have emerged as a cornerstone in Gr
Externí odkaz:
http://arxiv.org/abs/2404.14928
In the current landscape, the predominant methods for identifying manufacturing capabilities from manufacturers rely heavily on keyword matching and semantic matching. However, these methods often fall short by either overlooking valuable hidden info
Externí odkaz:
http://arxiv.org/abs/2403.17239
In an era of information explosion, recommender systems are vital tools to deliver personalized recommendations for users. The key of recommender systems is to forecast users' future behaviors based on previous user-item interactions. Due to their st
Externí odkaz:
http://arxiv.org/abs/2402.13973
Autor:
Wang, Hanbing, Liu, Xiaorui, Fan, Wenqi, Zhao, Xiangyu, Kini, Venkataramana, Yadav, Devendra, Wang, Fei, Wen, Zhen, Tang, Jiliang, Liu, Hui
Recently, sequential recommendation has been adapted to the LLM paradigm to enjoy the power of LLMs. LLM-based methods usually formulate recommendation information into natural language and the model is trained to predict the next item in an auto-reg
Externí odkaz:
http://arxiv.org/abs/2402.09543
Learning from Text-Attributed Graphs (TAGs) has attracted significant attention due to its wide range of real-world applications. The rapid evolution of language models (LMs) has revolutionized the way we process textual data, which indicates a stron
Externí odkaz:
http://arxiv.org/abs/2312.04737