Search Results for author: Kun He

Found 93 papers, 44 papers with code

Diversified Node Sampling based Hierarchical Transformer Pooling for Graph Representation Learning

no code implementations31 Oct 2023 Gaichao Li, Jinsong Chen, John E. Hopcroft, Kun He

Graph pooling methods have been widely used on downsampling graphs, achieving impressive results on multiple graph-level tasks like graph classification and graph generation.

Graph Classification Graph Generation +1

SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning

no code implementations17 Oct 2023 Jinsong Chen, Gaichao Li, John E. Hopcroft, Kun He

In this way, SignGT could learn informative node representations from both long-range dependencies and local topology information.

Graph Representation Learning Node Classification

FABind: Fast and Accurate Protein-Ligand Binding

1 code implementation10 Oct 2023 Qizhi Pei, Kaiyuan Gao, Lijun Wu, Jinhua Zhu, Yingce Xia, Shufang Xie, Tao Qin, Kun He, Tie-Yan Liu, Rui Yan

In this work, we propose $\mathbf{FABind}$, an end-to-end model that combines pocket prediction and docking to achieve accurate and fast protein-ligand binding.

Drug Discovery Pose Estimation +1

Long-range Meta-path Search through Progressive Sampling on Large-scale Heterogeneous Information Networks

2 code implementations17 Jul 2023 Chao Li, Zijie Guo, Qiuting He, Hao Xu, Kun He

Utilizing long-range dependency, though extensively studied in homogeneous graphs, is rarely studied in large-scale heterogeneous information networks (HINs), whose main challenge is the high costs and the difficulty in utilizing effective information.

Node Classification Node Property Prediction

Sampling-based Fast Gradient Rescaling Method for Highly Transferable Adversarial Attacks

no code implementations6 Jul 2023 Xu Han, Anmin Liu, Chenxuan Yao, Yanbo Fan, Kun He

In either case, the common gradient-based methods generally use the sign function to generate perturbations on the gradient update, that offers a roughly correct direction and has gained great success.

Rethinking the Backward Propagation for Adversarial Transferability

2 code implementations22 Jun 2023 Xiaosen Wang, Kangheng Tong, Kun He

input image and loss function so as to generate adversarial examples with higher transferability.

Knowledge Distillation via Token-level Relationship Graph

no code implementations20 Jun 2023 Shuoxi Zhang, Hanpeng Liu, Kun He

To address the above limitations, we propose a novel method called Knowledge Distillation with Token-level Relationship Graph (TRG) that leverages the token-wise relational knowledge to enhance the performance of knowledge distillation.

Knowledge Distillation Transfer Learning

Two Independent Teachers are Better Role Model

1 code implementation9 Jun 2023 Afifa Khaled, Ahmed A. Mubarak, Kun He

In this work, we address the above limitations by designing a new deep-learning model, called 3D-DenseUNet, which works as adaptable global aggregation blocks in down-sampling to solve the issue of spatial information loss.

Brain Segmentation

Tokenized Graph Transformer with Neighborhood Augmentation for Node Classification in Large Graphs

no code implementations22 May 2023 Jinsong Chen, Chang Liu, Kaiyuan Gao, Gaichao Li, Kun He

Graph Transformers, emerging as a new architecture for graph representation learning, suffer from the quadratic complexity on the number of nodes when handling large graphs.

Data Augmentation Graph Representation Learning +1

AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation

no code implementations CVPR 2023 Takehiko Ohkawa, Kun He, Fadime Sener, Tomas Hodan, Luan Tran, Cem Keskin

To obtain high-quality 3D hand pose annotations for the egocentric images, we develop an efficient pipeline, where we use an initial set of manual annotations to train a model to automatically annotate a much larger dataset.

3D Hand Pose Estimation Action Classification

Meta-multigraph Search: Rethinking Meta-structure on Heterogeneous Information Networks

no code implementations23 Apr 2023 Chao Li, Hao Xu, Kun He

Meta-structures are widely used to define which subset of neighbors to aggregate information in heterogeneous information networks (HINs).

Node Classification

Pointerformer: Deep Reinforced Multi-Pointer Transformer for the Traveling Salesman Problem

1 code implementation19 Apr 2023 Yan Jin, Yuandong Ding, Xuanhao Pan, Kun He, Li Zhao, Tao Qin, Lei Song, Jiang Bian

Traveling Salesman Problem (TSP), as a classic routing optimization problem originally arising in the domain of transportation and logistics, has become a critical task in broader domains, such as manufacturing and biology.

Traveling Salesman Problem

PIAT: Parameter Interpolation based Adversarial Training for Image Classification

no code implementations24 Mar 2023 Kun He, Xin Liu, Yichen Yang, Zhou Qin, Weigao Wen, Hui Xue, John E. Hopcroft

Besides, we suggest to use the Normalized Mean Square Error (NMSE) to further improve the robustness by aligning the clean and adversarial examples.

Image Classification

GMConv: Modulating Effective Receptive Fields for Convolutional Kernels

no code implementations9 Feb 2023 Qi Chen, Chao Li, Jia Ning, Stephen Lin, Kun He

Inspired by the property that ERFs typically exhibit a Gaussian distribution, we propose a Gaussian Mask convolutional kernel (GMConv) in this work.

Image Classification object-detection +1

Semantic Adversarial Attacks on Face Recognition through Significant Attributes

no code implementations28 Jan 2023 Yasmeen M. Khedr, Yifeng Xiong, Kun He

The probability score method is based on training a Face Verification model for an attribute prediction task to obtain a class probability score for each attribute.

Adversarial Attack Face Recognition +1

All in Tokens: Unifying Output Space of Visual Tasks via Soft Token

1 code implementation ICCV 2023 Jia Ning, Chen Li, Zheng Zhang, Zigang Geng, Qi Dai, Kun He, Han Hu

With these new techniques and other designs, we show that the proposed general-purpose task-solver can perform both instance segmentation and depth estimation well.

Instance Segmentation Monocular Depth Estimation +1

Incorporating Multi-armed Bandit with Local Search for MaxSAT

1 code implementation29 Nov 2022 Jiongzhi Zheng, Kun He, Jianrong Zhou, Yan Jin, Chu-min Li, Felip Manyà

In this paper, we propose a local search algorithm for these problems, called BandHS, which applies two multi-armed bandits to guide the search directions when escaping local optima.

Multi-Armed Bandits

Class-aware Information for Logit-based Knowledge Distillation

no code implementations27 Nov 2022 Shuoxi Zhang, Hanpeng Liu, John E. Hopcroft, Kun He

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 its superiority over logit-based distillation.

Knowledge Distillation

Differentiable Meta Multigraph Search with Partial Message Propagation on Heterogeneous Information Networks

no code implementations27 Nov 2022 Chao Li, Hao Xu, Kun He

To address these issues, we propose a novel method called Partial Message Meta Multigraph search (PMMM) to automatically optimize the neural architecture design on HINs.

Neural Architecture Search Node Classification

On the Complexity of Bayesian Generalization

1 code implementation20 Nov 2022 Yu-Zhe Shi, Manjie Xu, John E. Hopcroft, Kun He, Joshua B. Tenenbaum, Song-Chun Zhu, Ying Nian Wu, Wenjuan Han, Yixin Zhu

Specifically, at the $representational \ level$, we seek to answer how the complexity varies when a visual concept is mapped to the representation space.

Local Magnification for Data and Feature Augmentation

no code implementations15 Nov 2022 Kun He, Chang Liu, Stephen Lin, John E. Hopcroft

And further combination with our feature augmentation techniques, termed LOMA_IF&FO, can continue to strengthen the model and outperform advanced intensity transformation methods for data augmentation.

Data Augmentation Image Classification +2

Adaptive Multi-Neighborhood Attention based Transformer for Graph Representation Learning

no code implementations15 Nov 2022 Gaichao Li, Jinsong Chen, Kun He

MNA-GT further employs an attention layer to learn the importance of different attention kernels to enable the model to adaptively capture the graph structural information for different nodes.

Graph Representation Learning

Neighborhood Convolutional Network: A New Paradigm of Graph Neural Networks for Node Classification

no code implementations15 Nov 2022 Jinsong Chen, Boyu Li, Kun He

The decoupled Graph Convolutional Network (GCN), a recent development of GCN that decouples the neighborhood aggregation and feature transformation in each convolutional layer, has shown promising performance for graph representation learning.

Graph Representation Learning Node Classification

Incorporating Pre-training Paradigm for Antibody Sequence-Structure Co-design

no code implementations26 Oct 2022 Kaiyuan Gao, Lijun Wu, Jinhua Zhu, Tianbo Peng, Yingce Xia, Liang He, Shufang Xie, Tao Qin, Haiguang Liu, Kun He, Tie-Yan Liu

Specifically, we first pre-train an antibody language model based on the sequence data, then propose a one-shot way for sequence and structure generation of CDR to avoid the heavy cost and error propagation from an autoregressive manner, and finally leverage the pre-trained antibody model for the antigen-specific antibody generation model with some carefully designed modules.

Language Modelling Specificity

Hybrid Learning with New Value Function for the Maximum Common Subgraph Problem

no code implementations18 Aug 2022 Yanli Liu, Jiming Zhao, Chu-min Li, Hua Jiang, Kun He

Branch-and-Bound (BnB) is the basis of a class of efficient algorithms for MCS, consisting in successively selecting vertices to match and pruning when it is discovered that a solution better than the best solution found so far does not exist.

Reinforcement Learning (RL)

Generating Pseudo-labels Adaptively for Few-shot Model-Agnostic Meta-Learning

no code implementations9 Jul 2022 Guodong Liu, Tongling Wang, Shuoxi Zhang, Kun He

Model-Agnostic Meta-Learning (MAML) is a famous few-shot learning method that has inspired many follow-up efforts, such as ANIL and BOIL.

Few-Shot Learning Pseudo Label

Propagation with Adaptive Mask then Training for Node Classification on Attributed Networks

no code implementations21 Jun 2022 Jinsong Chen, Boyu Li, Qiuting He, Kun He

However, they follow the traditional structure-aware propagation strategy of GCNs, making it hard to capture the attribute correlation of nodes and sensitive to the structure noise described by edges whose two endpoints belong to different categories.

Node Classification

NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs

1 code implementation10 Jun 2022 Jinsong Chen, Kaiyuan Gao, Gaichao Li, Kun He

In this work, we observe that existing graph Transformers treat nodes as independent tokens and construct a single long sequence composed of all node tokens so as to train the Transformer model, causing it hard to scale to large graphs due to the quadratic complexity on the number of nodes for the self-attention computation.

Graph Learning Graph Mining +1

Enhancing the Robustness, Efficiency, and Diversity of Differentiable Architecture Search

no code implementations10 Apr 2022 Chao Li, Jia Ning, Han Hu, Kun He

Differentiable architecture search (DARTS) has attracted much attention due to its simplicity and significant improvement in efficiency.

Sampling-based Fast Gradient Rescaling Method for Highly Transferable Adversarial Attacks

no code implementations6 Apr 2022 Xu Han, Anmin Liu, Yifeng Xiong, Yanbo Fan, Kun He

Deviation between the original gradient and the generated noises may lead to inaccurate gradient update estimation and suboptimal solutions for adversarial transferability, which is crucial for black-box attacks.

Robust Textual Embedding against Word-level Adversarial Attacks

1 code implementation28 Feb 2022 Yichen Yang, Xiaosen Wang, Kun He

We attribute the vulnerability of natural language processing models to the fact that similar inputs are converted to dissimilar representations in the embedding space, leading to inconsistent outputs, and we propose a novel robust training method, termed Fast Triplet Metric Learning (FTML).

Metric Learning

TextHacker: Learning based Hybrid Local Search Algorithm for Text Hard-label Adversarial Attack

1 code implementation20 Jan 2022 Zhen Yu, Xiaosen Wang, Wanxiang Che, Kun He

Existing textual adversarial attacks usually utilize the gradient or prediction confidence to generate adversarial examples, making it hard to be deployed in real-world applications.

Adversarial Attack Hard-label Attack +3

BandMaxSAT: A Local Search MaxSAT Solver with Multi-armed Bandit

no code implementations14 Jan 2022 Jiongzhi Zheng, Kun He, Jianrong Zhou, Yan Jin, Chu-min Li, Felip Manya

We address Partial MaxSAT (PMS) and Weighted PMS (WPMS), two practical generalizations of the MaxSAT problem, and propose a local search algorithm for these problems, called BandMaxSAT, that applies a multi-armed bandit model to guide the search direction.

Rethinking the Data Annotation Process for Multi-view 3D Pose Estimation with Active Learning and Self-Training

1 code implementation27 Dec 2021 Qi Feng, Kun He, He Wen, Cem Keskin, Yuting Ye

Notably, on CMU Panoptic Studio, we are able to reduce the turn-around time by 60% and annotation cost by 80% when compared to the conventional annotation process.

3D Pose Estimation Active Learning +1

Triangle Attack: A Query-efficient Decision-based Adversarial Attack

1 code implementation13 Dec 2021 Xiaosen Wang, Zeliang Zhang, Kangheng Tong, Dihong Gong, Kun He, Zhifeng Li, Wei Liu

Decision-based attack poses a severe threat to real-world applications since it regards the target model as a black box and only accesses the hard prediction label.

Adversarial Attack Dimensionality Reduction

Uncovering the Local Hidden Community Structure in Social Networks

no code implementations8 Dec 2021 Meng Wang, Boyu Li, Kun He, John E. Hopcroft

We theoretically show that our method can avoid some situations that a broken community and the local community are regarded as one community in the subgraph, leading to the inaccuracy on detection which can be caused by global hidden community detection methods.

Local Community Detection

Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability

1 code implementation CVPR 2022 Yifeng Xiong, Jiadong Lin, Min Zhang, John E. Hopcroft, Kun He

The black-box adversarial attack has attracted impressive attention for its practical use in the field of deep learning security.

Adversarial Attack

Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackers

5 code implementations17 Nov 2021 Delv Lin, Qi Chen, Chengyu Zhou, Kun He

Multi-Object Tracking (MOT) has achieved aggressive progress and derived many excellent deep learning trackers.

Adversarial Attack Multi-Object Tracking +1

Stochastic Variance Reduced Ensemble Adversarial Attack

no code implementations29 Sep 2021 Jiadong Lin, Yifeng Xiong, Min Zhang, John E. Hopcroft, Kun He

Black-box adversarial attack has attracted much attention for its practical use in deep learning applications, and it is very challenging as there is no access to the architecture and weights of the target model.

Adversarial Attack

Detecting Textual Adversarial Examples through Randomized Substitution and Vote

1 code implementation13 Sep 2021 Xiaosen Wang, Yifeng Xiong, Kun He

Based on this observation, we propose a novel textual adversarial example detection method, termed Randomized Substitution and Vote (RS&V), which votes the prediction label by accumulating the logits of k samples generated by randomly substituting the words in the input text with synonyms.

TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting

1 code implementation EMNLP 2021 Haohai Sun, Jialun Zhong, Yunpu Ma, Zhen Han, Kun He

Compared with the completion task, the forecasting task is more difficult that faces two main challenges: (1) how to effectively model the time information to handle future timestamps?

Link Prediction reinforcement-learning +1

Regional Adversarial Training for Better Robust Generalization

no code implementations2 Sep 2021 Chuanbiao Song, Yanbo Fan, Yichen Yang, Baoyuan Wu, Yiming Li, Zhifeng Li, Kun He

Adversarial training (AT) has been demonstrated as one of the most promising defense methods against various adversarial attacks.

Farsighted Probabilistic Sampling: A General Strategy for Boosting Local Search MaxSAT Solvers

1 code implementation23 Aug 2021 Jiongzhi Zheng, Kun He, Jianrong Zhou

In this work, we observe that most local search (W)PMS solvers usually flip a single variable per iteration.

A New Entity Extraction Method Based on Machine Reading Comprehension

no code implementations14 Aug 2021 Xiaobo Jiang, Kun He, Jiajun He, Guangyu Yan

Entity extraction is a key technology for obtaining information from massive texts in natural language processing.

Machine Reading Comprehension

Crafting Adversarial Examples for Neural Machine Translation

no code implementations ACL 2021 Xinze Zhang, Junzhe Zhang, Zhenhua Chen, Kun He

We first show the current NMT adversarial attacks may be improperly estimated by the commonly used mono-directional translation, and we propose to leverage the round-trip translation technique to build valid metrics for evaluating NMT adversarial attacks.

Machine Translation NMT +2

Structure Amplification on Multi-layer Stochastic Block Models

no code implementations31 Jul 2021 Xiaodong Xin, Kun He, Jialu Bao, Bart Selman, John E. Hopcroft

Our previous work proposes a general structure amplification technique called HICODE that uncovers many layers of functional hidden structure in complex networks.

Stochastic Block Model

Reinforced Hybrid Genetic Algorithm for the Traveling Salesman Problem

no code implementations9 Jul 2021 Jiongzhi Zheng, Jialun Zhong, Menglei Chen, Kun He

In the hybrid algorithm, LKH can help EAX-GA improve the population by its effective local search, and EAX-GA can help LKH escape from local optima by providing high-quality and diverse initial solutions.

Q-Learning reinforcement-learning +2

Integrating Large Circular Kernels into CNNs through Neural Architecture Search

1 code implementation6 Jul 2021 Kun He, Chao Li, Yixiao Yang, Gao Huang, John E. Hopcroft

We first propose a simple yet efficient implementation of the convolution using circular kernels, and empirically show the significant advantages of large circular kernels over the counterpart square kernels.

Data Augmentation Neural Architecture Search

Multi-stage Optimization based Adversarial Training

no code implementations26 Jun 2021 Xiaosen Wang, Chuanbiao Song, LiWei Wang, Kun He

In this work, we aim to avoid the catastrophic overfitting by introducing multi-step adversarial examples during the single-step adversarial training.

Adversarial Robustness

Enhancing the Transferability of Adversarial Attacks through Variance Tuning

1 code implementation CVPR 2021 Xiaosen Wang, Kun He

Incorporating variance tuning with input transformations on iterative gradient-based attacks in the multi-model setting, the integrated method could achieve an average success rate of 90. 1% against nine advanced defense methods, improving the current best attack performance significantly by 85. 1% .

Boosting Adversarial Transferability through Enhanced Momentum

no code implementations19 Mar 2021 Xiaosen Wang, Jiadong Lin, Han Hu, Jingdong Wang, Kun He

Various momentum iterative gradient-based methods are shown to be effective to improve the adversarial transferability.

Adversarial Attack

Admix: Enhancing the Transferability of Adversarial Attacks

1 code implementation ICCV 2021 Xiaosen Wang, Xuanran He, Jingdong Wang, Kun He

We investigate in this direction and observe that existing transformations are all applied on a single image, which might limit the adversarial transferability.

AT-GAN: An Adversarial Generative Model for Non-constrained Adversarial Examples

no code implementations1 Jan 2021 Xiaosen Wang, Kun He, Chuanbiao Song, LiWei Wang, John E. Hopcroft

A recent work targets unrestricted adversarial example using generative model but their method is based on a search in the neighborhood of input noise, so actually their output is still constrained by input.

Adversarial Attack Transfer Learning

Tight Lower Complexity Bounds for Strongly Convex Finite-Sum Optimization

no code implementations17 Oct 2020 Min Zhang, Yao Shu, Kun He

Finite-sum optimization plays an important role in the area of machine learning, and hence has triggered a surge of interest in recent years.

Adversarial Training with Fast Gradient Projection Method against Synonym Substitution based Text Attacks

1 code implementation9 Aug 2020 Xiaosen Wang, Yichen Yang, Yihe Deng, Kun He

Adversarial training is the most empirically successful approach in improving the robustness of deep neural networks for image classification. For text classification, however, existing synonym substitution based adversarial attacks are effective but not efficient to be incorporated into practical text adversarial training.

Adversarial Attack Image Classification +2

Probability Learning based Tabu Search for the Budgeted Maximum Coverage Problem

no code implementations12 Jul 2020 Liwen Li, Zequn Wei, Jin-Kao Hao, Kun He

As the counterpart problem of SUKP, however, BMCP was introduced early in 1999 but since then it has been rarely studied, especially there is no practical algorithm proposed.

Dynamic Graph Correlation Learning for Disease Diagnosis with Incomplete Labels

no code implementations26 Feb 2020 Daizong Liu, Shuangjie Xu, Pan Zhou, Kun He, Wei Wei, Zichuan Xu

In this work, we propose a Disease Diagnosis Graph Convolutional Network (DD-GCN) that presents a novel view of investigating the inter-dependency among different diseases by using a dynamic learnable adjacency matrix in graph structure to improve the diagnosis accuracy.

Multi-Label Classification

Error-feedback stochastic modeling strategy for time series forecasting with convolutional neural networks

no code implementations3 Feb 2020 Xinze Zhang, Kun He, Yukun Bao

Despite the superiority of convolutional neural networks demonstrated in time series modeling and forecasting, it has not been fully explored on the design of the neural network architecture and the tuning of the hyper-parameters.

Time Series Time Series Forecasting

Stochastic Item Descent Method for Large Scale Equal Circle Packing Problem

no code implementations22 Jan 2020 Kun He, Min Zhang, Jianrong Zhou, Yan Jin, Chu-min Li

Inspired by its success in deep learning, we apply the idea of SGD with batch selection of samples to a classic optimization problem in decision version.

Adaptive Large Neighborhood Search for Circle Bin Packing Problem

no code implementations20 Jan 2020 Kun He, Kevin Tole, Fei Ni, Yong Yuan, Linyun Liao

We address a new variant of packing problem called the circle bin packing problem (CBPP), which is to find a dense packing of circle items to multiple square bins so as to minimize the number of used bins.

Single Image Reflection Removal through Cascaded Refinement

2 code implementations CVPR 2020 Chao Li, Yixiao Yang, Kun He, Stephen Lin, John E. Hopcroft

IBCLN is a cascaded network that iteratively refines the estimates of transmission and reflection layers in a manner that they can boost the prediction quality to each other, and information across steps of the cascade is transferred using an LSTM.

Community Detection Reflection Removal

Hierarchical hidden community detection for protein complex prediction

1 code implementation8 Oct 2019 Chao Li, Kun He, Guangshuai Liu, John E. Hopcroft

Results: We propose a method called HirHide (Hierarchical Hidden Community Detection), which can be combined with traditional community detection methods to enable them to discover hierarchical hidden communities.

Molecular Networks

Robust Local Features for Improving the Generalization of Adversarial Training

1 code implementation ICLR 2020 Chuanbiao Song, Kun He, Jiadong Lin, Li-Wei Wang, John E. Hopcroft

We continue to propose a new approach called Robust Local Features for Adversarial Training (RLFAT), which first learns the robust local features by adversarial training on the RBS-transformed adversarial examples, and then transfers the robust local features into the training of normal adversarial examples.

Natural Language Adversarial Defense through Synonym Encoding

1 code implementation15 Sep 2019 Xiaosen Wang, Hao Jin, Yichen Yang, Kun He

In the area of natural language processing, deep learning models are recently known to be vulnerable to various types of adversarial perturbations, but relatively few works are done on the defense side.

Adversarial Attack Adversarial Defense

Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks

1 code implementation ICLR 2020 Jiadong Lin, Chuanbiao Song, Kun He, Li-Wei Wang, John E. Hopcroft

While SIM is based on our discovery on the scale-invariant property of deep learning models, for which we leverage to optimize the adversarial perturbations over the scale copies of the input images so as to avoid "overfitting" on the white-box model being attacked and generate more transferable adversarial examples.

Adversarial Attack

Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency

1 code implementation ACL 2019 Shuhuai Ren, Yihe Deng, Kun He, Wanxiang Che

Experiments on three popular datasets using convolutional as well as LSTM models show that PWWS reduces the classification accuracy to the most extent, and keeps a very low word substitution rate.

Adversarial Attack General Classification +5

Adversarially Robust Generalization Just Requires More Unlabeled Data

1 code implementation3 Jun 2019 Runtian Zhai, Tianle Cai, Di He, Chen Dan, Kun He, John Hopcroft, Li-Wei Wang

Neural network robustness has recently been highlighted by the existence of adversarial examples.


A Learning based Branch and Bound for Maximum Common Subgraph Problems

no code implementations15 May 2019 Yan-li Liu, Chu-min Li, Hua Jiang, Kun He

Branch-and-bound (BnB) algorithms are widely used to solve combinatorial problems, and the performance crucially depends on its branching heuristic. In this work, we consider a typical problem of maximum common subgraph (MCS), and propose a branching heuristic inspired from reinforcement learning with a goal of reaching a tree leaf as early as possible to greatly reduce the search tree size. Extensive experiments show that our method is beneficial and outperforms current best BnB algorithm for the MCS.

reinforcement-learning Reinforcement Learning (RL)

A New Anchor Word Selection Method for the Separable Topic Discovery

no code implementations10 May 2019 Kun He, Wu Wang, Xiaosen Wang, John E. Hopcroft

In this work, we propose a new method for the anchor word selection by associating the word co-occurrence probability with the words similarity and assuming that the most different words on semantic are potential candidates for the anchor words.

Word Similarity

AT-GAN: An Adversarial Generator Model for Non-constrained Adversarial Examples

no code implementations16 Apr 2019 Xiaosen Wang, Kun He, Chuanbiao Song, Li-Wei Wang, John E. Hopcroft

In this way, AT-GAN can learn the distribution of adversarial examples that is very close to the distribution of real data.

Adversarial Attack

Effective reinforcement learning based local search for the maximum k-plex problem

no code implementations13 Mar 2019 Yan Jin, John H. Drake, Una Benlic, Kun He

The maximum k-plex problem is a computationally complex problem, which emerged from graph-theoretic social network studies.

reinforcement-learning Reinforcement Learning (RL)

Child Gender Determination with Convolutional Neural Networks on Hand Radio-Graphs

no code implementations13 Nov 2018 Mumtaz A. Kaloi, Kun He

In this work we propose a technique called GDCNN (Gender Determination with Convolutional Neural Networks), where the left hand radio-graphs of the children between a wide range of ages in 1 month to 18 years are examined to determine the gender.

Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation

1 code implementation NeurIPS 2018 Liwei Wang, Lunjia Hu, Jiayuan Gu, Yue Wu, Zhiqiang Hu, Kun He, John Hopcroft

The theory gives a complete characterization of the structure of neuron activation subspace matches, where the core concepts are maximum match and simple match which describe the overall and the finest similarity between sets of neurons in two networks respectively.

Improving the Generalization of Adversarial Training with Domain Adaptation

2 code implementations ICLR 2019 Chuanbiao Song, Kun He, Li-Wei Wang, John E. Hopcroft

Our intuition is to regard the adversarial training on FGSM adversary as a domain adaption task with limited number of target domain samples.

Adversarial Attack Domain Adaptation

An Iterative Path-Breaking Approach with Mutation and Restart Strategies for the MAX-SAT Problem

no code implementations10 Aug 2018 Zhen-Xing Xu, Kun He, Chu-min Li

Although Path-Relinking is an effective local search method for many combinatorial optimization problems, its application is not straightforward in solving the MAX-SAT, an optimization variant of the satisfiability problem (SAT) that has many real-world applications and has gained more and more attention in academy and industry.

Combinatorial Optimization

Hashing with Binary Matrix Pursuit

2 code implementations ECCV 2018 Fatih Cakir, Kun He, Stan Sclaroff

We propose theoretical and empirical improvements for two-stage hashing methods.

Image Retrieval Retrieval

Local Descriptors Optimized for Average Precision

no code implementations CVPR 2018 Kun He, Yan Lu, Stan Sclaroff

In this paper, we improve the learning of local feature descriptors by optimizing the performance of descriptor matching, which is a common stage that follows descriptor extraction in local feature based pipelines, and can be formulated as nearest neighbor retrieval.

Learning-To-Rank Retrieval

Multilevel Language and Vision Integration for Text-to-Clip Retrieval

1 code implementation13 Apr 2018 Huijuan Xu, Kun He, Bryan A. Plummer, Leonid Sigal, Stan Sclaroff, Kate Saenko

To capture the inherent structures present in both text and video, we introduce a multilevel model that integrates vision and language features earlier and more tightly than prior work.


Hashing with Mutual Information

2 code implementations2 Mar 2018 Fatih Cakir, Kun He, Sarah Adel Bargal, Stan Sclaroff

Binary vector embeddings enable fast nearest neighbor retrieval in large databases of high-dimensional objects, and play an important role in many practical applications, such as image and video retrieval.

Image Retrieval Retrieval +1

Krylov Subspace Approximation for Local Community Detection

2 code implementations13 Dec 2017 Kun He, Pan Shi, David Bindel, John E. Hopcroft

Community detection is an important information mining task in many fields including computer science, social sciences, biology and physics.

Social and Information Networks

The Local Dimension of Deep Manifold

no code implementations5 Nov 2017 Mengxiao Zhang, Wangquan Wu, Yanren Zhang, Kun He, Tao Yu, Huan Long, John E. Hopcroft

Our results show that the dimensions of different categories are close to each other and decline quickly along the convolutional layers and fully connected layers.

Predicting Foreground Object Ambiguity and Efficiently Crowdsourcing the Segmentation(s)

no code implementations30 Apr 2017 Danna Gurari, Kun He, Bo Xiong, Jianming Zhang, Mehrnoosh Sameki, Suyog Dutt Jain, Stan Sclaroff, Margrit Betke, Kristen Grauman

We propose the ambiguity problem for the foreground object segmentation task and motivate the importance of estimating and accounting for this ambiguity when designing vision systems.

Semantic Segmentation valid

Randomness in Deconvolutional Networks for Visual Representation

no code implementations2 Apr 2017 Kun He, Jingbo Wang, Haochuan Li, Yao Shu, Mengxiao Zhang, Man Zhu, Li-Wei Wang, John E. Hopcroft

Toward a deeper understanding on the inner work of deep neural networks, we investigate CNN (convolutional neural network) using DCN (deconvolutional network) and randomization technique, and gain new insights for the intrinsic property of this network architecture.

General Classification Image Reconstruction

MIHash: Online Hashing with Mutual Information

1 code implementation ICCV 2017 Fatih Cakir, Kun He, Sarah Adel Bargal, Stan Sclaroff

Learning-based hashing methods are widely used for nearest neighbor retrieval, and recently, online hashing methods have demonstrated good performance-complexity trade-offs by learning hash functions from streaming data.

Image Retrieval Retrieval

Hidden Community Detection in Social Networks

4 code implementations24 Feb 2017 Kun He, Yingru Li, Sucheta Soundarajan, John E. Hopcroft

We introduce a new paradigm that is important for community detection in the realm of network analysis.

Community Detection

A Powerful Generative Model Using Random Weights for the Deep Image Representation

1 code implementation NeurIPS 2016 Kun He, Yan Wang, John Hopcroft

To our knowledge this is the first demonstration of image representations using untrained deep neural networks.

Uncovering the Small Community Structure in Large Networks: A Local Spectral Approach

1 code implementation25 Sep 2015 Yixuan Li, Kun He, David Bindel, John Hopcroft

Nowadays, as we often explore networks with billions of vertices and find communities of size hundreds, it is crucial to shift our attention from macroscopic structure to microscopic structure when dealing with large networks.

Social and Information Networks Data Structures and Algorithms Physics and Society G.2.2; H.3.3

Generalized Majorization-Minimization

no code implementations25 Jun 2015 Sobhan Naderi Parizi, Kun He, Reza Aghajani, Stan Sclaroff, Pedro Felzenszwalb

Majorization-Minimization (MM) is a powerful iterative procedure for optimizing non-convex functions that works by optimizing a sequence of bounds on the function.

Revealing Multiple Layers of Hidden Community Structure in Networks

2 code implementations23 Jan 2015 Kun He, Sucheta Soundarajan, Xuezhi Cao, John Hopcroft, Menglong Huang

Additionally, on both real and synthetic networks containing a hidden ground-truth community structure, HICODE uncovers this structure better than any baseline algorithms that we compared against.

Social and Information Networks Physics and Society

Cannot find the paper you are looking for? You can Submit a new open access paper.