5 citations · 10 across the 7 of their papers we have counts for
7 papers
Label Ensemble Perspective for Reduced-Complexity Graph Node Classification under Label Noise
Rui Zhao, Bin Shi, Zhiming Liang +4
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 \emph{…
Graph Adversarial Diffusion Convolution
Songtao Liu, Jinghui Chen, Tianfan Fu +3
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…
Biharmonic Distance of Graphs and its Higher-Order Variants: Theoretical Properties with Applications to Centrality and Clustering
Mitchell Black, Lucy Lin, Amir Nayyeri +1
Effective resistance is a distance between vertices of a graph that is both theoretically interesting and useful in applications. We study a variant of effective resistance called…
Backdoor Contrastive Learning via Bi-level Trigger Optimization
Weiyu Sun, Xinyu Zhang, Hao Lu +4
Contrastive Learning (CL) has attracted enormous attention due to its remarkable capability in unsupervised representation learning. However, recent works have revealed the vulnera…
On the Safety of Open-Sourced Large Language Models: Does Alignment Really Prevent Them From Being Misused?
Hangfan Zhang, Zhimeng Guo, Huaisheng Zhu +5
Large Language Models (LLMs) have achieved unprecedented performance in Natural Language Generation (NLG) tasks. However, many existing studies have shown that they could be misuse…
How Powerful is Implicit Denoising in Graph Neural Networks
Songtao Liu, Rex Ying, Hanze Dong +3
Graph Neural Networks (GNNs), which aggregate features from neighbors, are widely used for graph-structured data processing due to their powerful representation learning capabiliti…
FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning
Songtao Liu, Zhengkai Tu, Minkai Xu +6
Retrosynthetic planning aims to devise a complete multi-step synthetic route from starting materials to a target molecule. Current strategies use a decoupled approach of single-ste…