453 citations · 1.5k across the 44 of their papers we have counts for
48 papers
Parameter Interpolation Adversarial Training for Robust Image Classification
Xin Liu, Yichen Yang, Kun He +1
Though deep neural networks exhibit superior performance on various tasks, they are still plagued by adversarial examples. Adversarial training has been demonstrated to be the most…
Learning to Rewrite Prompts for Bootstrapping LLMs on Downstream Tasks
Qinhao Zhou, Xiang Xiang, Kun He +1
In recent years, the growing interest in Large Language Models (LLMs) has significantly advanced prompt engineering, transitioning from manual design to model-based optimization. P…
DAM-GT: Dual Positional Encoding-Based Attention Masking Graph Transformer for Node Classification
Chenyang Li, Jinsong Chen, John E. Hopcroft +1
Neighborhood-aware tokenized graph Transformers have recently shown great potential for node classification tasks. Despite their effectiveness, our in-depth analysis of neighborhoo…
Enhancing Pre-Trained Model-Based Class-Incremental Learning through Neural Collapse
Kun He, Zijian Song, Shuoxi Zhang +1
Class-Incremental Learning (CIL) is a critical capability for real-world applications, enabling learning systems to adapt to new tasks while retaining knowledge from previous ones.…
Rethinking Tokenized Graph Transformers for Node Classification
Jinsong Chen, Chenyang Li, GaiChao Li +2
Node tokenized graph Transformers (GTs) have shown promising performance in node classification. The generation of token sequences is the key module in existing tokenized GTs which…
Tokenizing 3D Molecule Structure with Quantized Spherical Coordinates
Kaiyuan Gao, Yusong Wang, Haoxiang Guan +5
The application of language models (LMs) to molecular structure generation using line notations such as SMILES and SELFIES has been well-established in the field of cheminformatics…
Leveraging Contrastive Learning for Enhanced Node Representations in Tokenized Graph Transformers
Jinsong Chen, Hanpeng Liu, John E. Hopcroft +1
While tokenized graph Transformers have demonstrated strong performance in node classification tasks, their reliance on a limited subset of nodes with high similarity scores for co…
Diversified Node Sampling based Hierarchical Transformer Pooling for Graph Representation Learning
Gaichao Li, Jinsong Chen, John E. Hopcroft +1
Graph pooling methods have been widely used on downsampling graphs, achieving impressive results on multiple graph-level tasks like graph classification and graph generation. An im…
SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning
Jinsong Chen, Gaichao Li, John E. Hopcroft +1
The emerging graph Transformers have achieved impressive performance for graph representation learning over graph neural networks (GNNs). In this work, we regard the self-attention…
PIAT: Parameter Interpolation based Adversarial Training for Image Classification
Kun He, Xin Liu, Yichen Yang +4
Adversarial training has been demonstrated to be the most effective approach to defend against adversarial attacks. However, existing adversarial training methods show apparent osc…
Class-aware Information for Logit-based Knowledge Distillation
Shuoxi Zhang, Hanpeng Liu, John E. Hopcroft +1
Knowledge distillation aims to transfer knowledge to the student model by utilizing the predictions/features of the teacher model, and feature-based distillation has recently shown…
On the Complexity of Bayesian Generalization
Yu-Zhe Shi, Manjie Xu, John E. Hopcroft +6
We consider concept generalization at a large scale in the diverse and natural visual spectrum. Established computational modes (i.e., rule-based or similarity-based) are primarily…
Local Magnification for Data and Feature Augmentation
Kun He, Chang Liu, Stephen Lin +1
In recent years, many data augmentation techniques have been proposed to increase the diversity of input data and reduce the risk of overfitting on deep neural networks. In this wo…
HoSIM: Higher-order Structural Importance based Method for Multiple Local Community Detection
Boyu Li, Meng Wang, John E. Hopcroft +1
Local community detection has attracted much research attention recently, and many methods have been proposed for the single local community detection that finds a community contai…
Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power
Binghui Li, Jikai Jin, Han Zhong +2
It is well-known that modern neural networks are vulnerable to adversarial examples. To mitigate this problem, a series of robust learning algorithms have been proposed. However, a…
Uncovering the Local Hidden Community Structure in Social Networks
Meng Wang, Boyu Li, Kun He +1
Hidden community is a useful concept proposed recently for social network analysis. To handle the rapid growth of network scale, in this work, we explore the detection of hidden co…
Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability
Yifeng Xiong, Jiadong Lin, Min Zhang +2
The black-box adversarial attack has attracted impressive attention for its practical use in the field of deep learning security. Meanwhile, it is very challenging as there is no a…
Structure Amplification on Multi-layer Stochastic Block Models
Xiaodong Xin, Kun He, Jialu Bao +2
Much of the complexity of social, biological, and engineered systems arises from a network of complex interactions connecting many basic components. Network analysis tools have bee…
Integrating Large Circular Kernels into CNNs through Neural Architecture Search
Kun He, Chao Li, Yixiao Yang +2
The square kernel is a standard unit for contemporary CNNs, as it fits well on the tensor computation for convolution operation. However, the retinal ganglion cells in the biologic…
Hidden Community Detection on Two-layer Stochastic Models: a Theoretical Perspective
Jialu Bao, Kun He, Xiaodong Xin +2
Hidden community is a new graph-theoretical concept recently proposed [4], in which the authors also propose a meta-approach called HICODE (Hidden Community Detection) for detectin…
Single Image Reflection Removal through Cascaded Refinement
Chao Li, Yixiao Yang, Kun He +2
We address the problem of removing undesirable reflections from a single image captured through a glass surface, which is an ill-posed, challenging but practically important proble…
Hierarchical hidden community detection for protein complex prediction
Chao Li, Kun He, Guangshuai Liu +1
Motivation: Discovering functional modules in protein-protein interaction (PPI) networks by optimization methods remains a longstanding challenge in biology. Traditional algorithms…
Robust Local Features for Improving the Generalization of Adversarial Training
Chuanbiao Song, Kun He, Jiadong Lin +2
Adversarial training has been demonstrated as one of the most effective methods for training robust models to defend against adversarial examples. However, adversarially trained mo…
Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks
Jiadong Lin, Chuanbiao Song, Kun He +2
Deep learning models are vulnerable to adversarial examples crafted by applying human-imperceptible perturbations on benign inputs. However, under the black-box setting, most exist…