Zobrazeno 1 - 10
of 11 543
pro vyhledávání: '"LIN, Lu"'
Graph Neural Networks (GNNs) have been widely employed for semi-supervised node classification tasks on graphs. However, the performance of GNNs is significantly affected by label noise, that is, a small amount of incorrectly labeled nodes can substa
Externí odkaz:
http://arxiv.org/abs/2411.11020
Recent advances in diffusion models have significantly enhanced the quality of image synthesis, yet they have also introduced serious safety concerns, particularly the generation of Not Safe for Work (NSFW) content. Previous research has demonstrated
Externí odkaz:
http://arxiv.org/abs/2410.21471
Distribution shifts between training and testing datasets significantly impair the model performance on graph learning. A commonly-taken causal view in graph invariant learning suggests that stable predictive features of graphs are causally associate
Externí odkaz:
http://arxiv.org/abs/2410.17506
Deep learning-based industrial anomaly detection models have achieved remarkably high accuracy on commonly used benchmark datasets. However, the robustness of those models may not be satisfactory due to the existence of adversarial examples, which po
Externí odkaz:
http://arxiv.org/abs/2408.04839
Contemporary language models are increasingly multilingual, but Chinese LLM developers must navigate complex political and business considerations of language diversity. Language policy in China aims at influencing the public discourse and governing
Externí odkaz:
http://arxiv.org/abs/2407.09652
This paper introduces a min-max optimization formulation for the Graph Signal Denoising (GSD) problem. In this formulation, we first maximize the second term of GSD by introducing perturbations to the graph structure based on Laplacian distance and t
Externí odkaz:
http://arxiv.org/abs/2406.02059
Large Language Models (LLMs) have demonstrated impressive performances in complex text generation tasks. However, the contribution of the input prompt to the generated content still remains obscure to humans, underscoring the necessity of elucidating
Externí odkaz:
http://arxiv.org/abs/2405.20404
Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications. While fine-tuning seems to be a direct solution, it requires substantial computational reso
Externí odkaz:
http://arxiv.org/abs/2406.00045
The recent breakthrough in large language models (LLMs) such as ChatGPT has revolutionized production processes at an unprecedented pace. Alongside this progress also comes mounting concerns about LLMs' susceptibility to jailbreaking attacks, which l
Externí odkaz:
http://arxiv.org/abs/2405.14023
Contrastive Learning (CL) has attracted enormous attention due to its remarkable capability in unsupervised representation learning. However, recent works have revealed the vulnerability of CL to backdoor attacks: the feature extractor could be misle
Externí odkaz:
http://arxiv.org/abs/2404.07863