Search Results for author: Ivor W. Tsang

Found 98 papers, 22 papers with code

Diversified Batch Selection for Training Acceleration

1 code implementation7 Jun 2024 Feng Hong, Yueming Lyu, Jiangchao Yao, Ya zhang, Ivor W. Tsang, Yanfeng Wang

The remarkable success of modern machine learning models on large datasets often demands extensive training time and resource consumption.

Diversity

Covariance-Adaptive Sequential Black-box Optimization for Diffusion Targeted Generation

no code implementations2 Jun 2024 Yueming Lyu, Kim Yong Tan, Yew Soon Ong, Ivor W. Tsang

Diffusion models have demonstrated great potential in generating high-quality content for images, natural language, protein domains, etc.

3D Molecule Generation

Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient

no code implementations28 May 2024 Hao Di, Haishan Ye, Yueling Zhang, Xiangyu Chang, Guang Dai, Ivor W. Tsang

Variance reduction techniques are designed to decrease the sampling variance, thereby accelerating convergence rates of first-order (FO) and zeroth-order (ZO) optimization methods.

HC$^2$L: Hybrid and Cooperative Contrastive Learning for Cross-lingual Spoken Language Understanding

no code implementations10 May 2024 Bowen Xing, Ivor W. Tsang

State-of-the-art model for zero-shot cross-lingual spoken language understanding performs cross-lingual unsupervised contrastive learning to achieve the label-agnostic semantic alignment between each utterance and its code-switched data.

Contrastive Learning Spoken Language Understanding

Collaborative Knowledge Infusion for Low-resource Stance Detection

no code implementations28 Mar 2024 Ming Yan, Joey Tianyi Zhou, Ivor W. Tsang

Specifically, our stance detection approach leverages target background knowledge collaboratively from different knowledge sources with the help of knowledge alignment.

Stance Detection

Second-Order Fine-Tuning without Pain for LLMs:A Hessian Informed Zeroth-Order Optimizer

no code implementations23 Feb 2024 Yanjun Zhao, Sizhe Dang, Haishan Ye, Guang Dai, Yi Qian, Ivor W. Tsang

Fine-tuning large language models (LLMs) with classic first-order optimizers entails prohibitive GPU memory due to the backpropagation process.

Transductive Reward Inference on Graph

no code implementations6 Feb 2024 Bohao Qu, Xiaofeng Cao, Qing Guo, Yi Chang, Ivor W. Tsang, Chengqi Zhang

In this study, we present a transductive inference approach on that reward information propagation graph, which enables the effective estimation of rewards for unlabelled data in offline reinforcement learning.

reinforcement-learning

Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting

no code implementations22 Jan 2024 Jinliang Deng, Feiyang Ye, Du Yin, Xuan Song, Ivor W. Tsang, Hui Xiong

Long-term time series forecasting (LTSF) represents a critical frontier in time series analysis, characterized by extensive input sequences, as opposed to the shorter spans typical of traditional approaches.

Time Series Time Series Forecasting

Leveraging Open-Vocabulary Diffusion to Camouflaged Instance Segmentation

no code implementations29 Dec 2023 Tuan-Anh Vu, Duc Thanh Nguyen, Qing Guo, Binh-Son Hua, Nhat Minh Chung, Ivor W. Tsang, Sai-Kit Yeung

Such cross-domain representations are desirable in segmenting camouflaged objects where visual cues are subtle to distinguish the objects from the background, especially in segmenting novel objects which are not seen in training.

Instance Segmentation Segmentation +1

Exploiting Contextual Target Attributes for Target Sentiment Classification

no code implementations21 Dec 2023 Bowen Xing, Ivor W. Tsang

The attributes contain the background and property information of the target, which can help to enrich the semantics of the review context and the target.

Attribute Classification +4

Co-guiding for Multi-intent Spoken Language Understanding

no code implementations22 Nov 2023 Bowen Xing, Ivor W. Tsang

For the first stage, we propose single-task supervised contrastive learning, and for the second stage, we propose co-guiding supervised contrastive learning, which considers the two tasks' mutual guidances in the contrastive learning procedure.

Contrastive Learning Graph Attention +3

Aggregation Weighting of Federated Learning via Generalization Bound Estimation

no code implementations10 Nov 2023 Mingwei Xu, Xiaofeng Cao, Ivor W. Tsang, James T. Kwok

In this paper, we replace the aforementioned weighting method with a new strategy that considers the generalization bounds of each local model.

Federated Learning Generalization Bounds

Sanitized Clustering against Confounding Bias

1 code implementation2 Nov 2023 Yinghua Yao, Yuangang Pan, Jing Li, Ivor W. Tsang, Xin Yao

Therein, the interested clustering factor and the confounding factor are coarsely considered in the raw feature space, where the correlation between the data and the confounding factor is ideally assumed to be linear for convenient solutions.

Clustering

Ladder-of-Thought: Using Knowledge as Steps to Elevate Stance Detection

no code implementations31 Aug 2023 Kairui Hu, Ming Yan, Joey Tianyi Zhou, Ivor W. Tsang, Wen Haw Chong, Yong Keong Yap

In response to these identified gaps, we introduce the Ladder-of-Thought (LoT) for the stance detection task.

Stance Detection

Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold

no code implementations21 Aug 2023 Jun Chen, Haishan Ye, Mengmeng Wang, Tianxin Huang, Guang Dai, Ivor W. Tsang, Yong liu

This paper proposes a decentralized Riemannian conjugate gradient descent (DRCGD) method that aims at minimizing a global function over the Stiefel manifold.

Second-order methods

Relational Temporal Graph Reasoning for Dual-task Dialogue Language Understanding

no code implementations15 Jun 2023 Bowen Xing, Ivor W. Tsang

In this paper, we put forward a new framework, whose core is relational temporal graph reasoning. We propose a speaker-aware temporal graph (SATG) and a dual-task relational temporal graph (DRTG) to facilitate relational temporal modeling in dialog understanding and dual-task reasoning.

Sentiment Analysis Sentiment Classification

Co-evolving Graph Reasoning Network for Emotion-Cause Pair Extraction

no code implementations7 Jun 2023 Bowen Xing, Ivor W. Tsang

Finally, we propose a Co-evolving Graph Reasoning Network (CGR-Net) that implements our MTL framework and conducts Co-evolving Reasoning on MRG.

Emotion-Cause Pair Extraction Multi-Task Learning

On the Robustness of Segment Anything

no code implementations25 May 2023 Yihao Huang, Yue Cao, Tianlin Li, Felix Juefei-Xu, Di Lin, Ivor W. Tsang, Yang Liu, Qing Guo

Second, we extend representative adversarial attacks against SAM and study the influence of different prompts on robustness.

Autonomous Vehicles valid

Earning Extra Performance from Restrictive Feedbacks

1 code implementation28 Apr 2023 Jing Li, Yuangang Pan, Yueming Lyu, Yinghua Yao, Yulei Sui, Ivor W. Tsang

Unlike existing model tuning methods where the target data is always ready for calculating model gradients, the model providers in EXPECTED only see some feedbacks which could be as simple as scalars, such as inference accuracy or usage rate.

UTSGAN: Unseen Transition Suss GAN for Transition-Aware Image-to-image Translation

no code implementations24 Apr 2023 Yaxin Shi, Xiaowei Zhou, Ping Liu, Ivor W. Tsang

Furthermore, we propose the use of transition consistency, defined on the transition variable, to enable regularization of consistency on unobserved translations, which is omitted in previous works.

Attribute Image-to-Image Translation +1

Adversary-Aware Partial label learning with Label distillation

no code implementations2 Apr 2023 Cheng Chen, Yueming Lyu, Ivor W. Tsang

However, conventional partial-label learning (PLL) methods are still vulnerable to the high ratio of noisy partial labels, especially in a large labelling space.

Partial Label Learning

Policy Dispersion in Non-Markovian Environment

no code implementations28 Feb 2023 Bohao Qu, Xiaofeng Cao, Jielong Yang, Hechang Chen, Chang Yi, Ivor W. Tsang, Yew-Soon Ong

To resolve this problem, this paper tries to learn the diverse policies from the history of state-action pairs under a non-Markovian environment, in which a policy dispersion scheme is designed for seeking diverse policy representation.

Latent Class-Conditional Noise Model

1 code implementation19 Feb 2023 Jiangchao Yao, Bo Han, Zhihan Zhou, Ya zhang, Ivor W. Tsang

We solve this problem by introducing a Latent Class-Conditional Noise model (LCCN) to parameterize the noise transition under a Bayesian framework.

Learning with noisy labels

Learning Discretized Neural Networks under Ricci Flow

no code implementations7 Feb 2023 Jun Chen, Hanwen Chen, Mengmeng Wang, Guang Dai, Ivor W. Tsang, Yong liu

By introducing a partial differential equation on metrics, i. e., the Ricci flow, we establish the dynamical stability and convergence of the LNE metric with the $L^2$-norm perturbation.

Structure-Informed Shadow Removal Networks

no code implementations9 Jan 2023 Yuhao Liu, Qing Guo, Lan Fu, Zhanghan Ke, Ke Xu, Wei Feng, Ivor W. Tsang, Rynson W. H. Lau

Hence, in this paper, we propose to remove shadows at the image structure level.

Shadow Removal

Coarse-to-Fine Contrastive Learning on Graphs

no code implementations13 Dec 2022 Peiyao Zhao, Yuangang Pan, Xin Li, Xu Chen, Ivor W. Tsang, Lejian Liao

Inspired by the impressive success of contrastive learning (CL), a variety of graph augmentation strategies have been employed to learn node representations in a self-supervised manner.

Contrastive Learning Learning-To-Rank

Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Filling

no code implementations19 Oct 2022 Bowen Xing, Ivor W. Tsang

Therefore, in this paper, we first construct a Heterogeneous Label Graph (HLG) containing two kinds of topologies: (1) statistical dependencies based on labels' co-occurrence patterns and hierarchies in slot labels; (2) rich relations among the label nodes.

Intent Detection slot-filling +1

Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs

1 code implementation19 Oct 2022 Bowen Xing, Ivor W. Tsang

In this paper, we propose a novel model termed Co-guiding Net, which implements a two-stage framework achieving the \textit{mutual guidances} between the two tasks.

Graph Attention Intent Detection +2

A Survey of Learning on Small Data: Generalization, Optimization, and Challenge

no code implementations29 Jul 2022 Xiaofeng Cao, Weixin Bu, Shengjun Huang, MinLing Zhang, Ivor W. Tsang, Yew Soon Ong, James T. Kwok

In future, learning on small data that approximates the generalization ability of big data is one of the ultimate purposes of AI, which requires machines to recognize objectives and scenarios relying on small data as humans.

Active Learning Contrastive Learning +4

Data-Efficient Learning via Minimizing Hyperspherical Energy

no code implementations30 Jun 2022 Xiaofeng Cao, Weiyang Liu, Ivor W. Tsang

Finally, we demonstrate the empirical performance of MHEAL in a wide range of applications on data-efficient learning, including deep clustering, distribution matching, version space sampling and deep active learning.

Active Learning Deep Clustering

Black-box Generalization of Machine Teaching

no code implementations30 Jun 2022 Xiaofeng Cao, Yaming Guo, Ivor W. Tsang, James T. Kwok

An inherent assumption is that this learning manner can derive those updates into the optimal hypothesis.

Active Learning

LADDER: Latent Boundary-guided Adversarial Training

1 code implementation8 Jun 2022 Xiaowei Zhou, Ivor W. Tsang, Jie Yin

To achieve a better trade-off between standard accuracy and adversarial robustness, we propose a novel adversarial training framework called LAtent bounDary-guided aDvErsarial tRaining (LADDER) that adversarially trains DNN models on latent boundary-guided adversarial examples.

Adversarial Robustness

Neural Subgraph Explorer: Reducing Noisy Information via Target-Oriented Syntax Graph Pruning

no code implementations23 May 2022 Bowen Xing, Ivor W. Tsang

In this paper, we propose a novel model termed Neural Subgraph Explorer, which (1) reduces the noisy information via pruning target-irrelevant nodes on the syntax graph; (2) introduces beneficial first-order connections between the target and its related words into the obtained graph.

Sentiment Analysis Sentiment Classification

Diverse Preference Augmentation with Multiple Domains for Cold-start Recommendations

no code implementations1 Apr 2022 Yan Zhang, Changyu Li, Ivor W. Tsang, Hui Xu, Lixin Duan, Hongzhi Yin, Wen Li, Jie Shao

Motivated by the idea of meta-augmentation, in this paper, by treating a user's preference over items as a task, we propose a so-called Diverse Preference Augmentation framework with multiple source domains based on meta-learning (referred to as MetaDPA) to i) generate diverse ratings in a new domain of interest (known as target domain) to handle overfitting on the case of sparse interactions, and to ii) learn a preference model in the target domain via a meta-learning scheme to alleviate cold-start issues.

Domain Adaptation Meta-Learning +1

DARER: Dual-task Temporal Relational Recurrent Reasoning Network for Joint Dialog Sentiment Classification and Act Recognition

1 code implementation Findings (ACL) 2022 Bowen Xing, Ivor W. Tsang

To implement our framework, we propose a novel model dubbed DARER, which first generates the context-, speaker- and temporal-sensitive utterance representations via modeling SATG, then conducts recurrent dual-task relational reasoning on DRTG, in which process the estimated label distributions act as key clues in prediction-level interactions.

Dialog Act Classification Relational Reasoning +2

Taming Overconfident Prediction on Unlabeled Data from Hindsight

no code implementations15 Dec 2021 Jing Li, Yuangang Pan, Ivor W. Tsang

The prediction uncertainty is typically expressed as the \emph{entropy} computed by the transformed probabilities in output space.

TRIP: Refining Image-to-Image Translation via Rival Preferences

no code implementations26 Nov 2021 Yinghua Yao, Yuangang Pan, Ivor W. Tsang, Xin Yao

In particular, we simultaneously train two modules: a generator that translates an input image to the desired image with smooth subtle changes with respect to the interested attributes; and a ranker that ranks rival preferences consisting of the input image and the desired image.

Attribute Image-to-Image Translation +1

Deep Safe Multi-Task Learning

no code implementations20 Nov 2021 Zhixiong Yue, Feiyang Ye, Yu Zhang, Christy Liang, Ivor W. Tsang

We theoretically study the safeness of both learning strategies in the DSMTL model to show that the proposed methods can achieve some versions of safe multi-task learning.

Multi-Task Learning

Edge but not Least: Cross-View Graph Pooling

no code implementations24 Sep 2021 Xiaowei Zhou, Jie Yin, Ivor W. Tsang

Graph neural networks have emerged as a powerful model for graph representation learning to undertake graph-level prediction tasks.

Graph Classification Graph Regression +1

A Multi-view Multi-task Learning Framework for Multi-variate Time Series Forecasting

1 code implementation2 Sep 2021 Jinliang Deng, Xiusi Chen, Renhe Jiang, Xuan Song, Ivor W. Tsang

Therefore, there are two fundamental views which can be used to analyze MTS data, namely the spatial view and the temporal view.

Attribute Multi-Task Learning +2

Differential-Critic GAN: Generating What You Want by a Cue of Preferences

1 code implementation14 Jul 2021 Yinghua Yao, Yuangang Pan, Ivor W. Tsang, Xin Yao

This paper proposes Differential-Critic Generative Adversarial Network (DiCGAN) to learn the distribution of user-desired data when only partial instead of the entire dataset possesses the desired property.

Generative Adversarial Network

Online Multi-Agent Forecasting with Interpretable Collaborative Graph Neural Network

no code implementations2 Jul 2021 Maosen Li, Siheng Chen, Yanning Shen, Genjia Liu, Ivor W. Tsang, Ya zhang

This paper considers predicting future statuses of multiple agents in an online fashion by exploiting dynamic interactions in the system.

Graph Neural Network Human motion prediction +1

Bayesian Active Learning by Disagreements: A Geometric Perspective

no code implementations6 May 2021 Xiaofeng Cao, Ivor W. Tsang

We present geometric Bayesian active learning by disagreements (GBALD), a framework that performs BALD on its core-set construction interacting with model uncertainty estimation.

Active Learning

Distribution Matching for Machine Teaching

no code implementations6 May 2021 Xiaofeng Cao, Ivor W. Tsang

This optimization solver is in general ineffective when the student learner does not disclose any cue of the learning parameters.

The Emerging Trends of Multi-Label Learning

no code implementations23 Nov 2020 Weiwei Liu, Haobo Wang, Xiaobo Shen, Ivor W. Tsang

Exabytes of data are generated daily by humans, leading to the growing need for new efforts in dealing with the grand challenges for multi-label learning brought by big data.

Classification Extreme Multi-Label Classification +2

A Survey of Label-noise Representation Learning: Past, Present and Future

1 code implementation9 Nov 2020 Bo Han, Quanming Yao, Tongliang Liu, Gang Niu, Ivor W. Tsang, James T. Kwok, Masashi Sugiyama

Classical machine learning implicitly assumes that labels of the training data are sampled from a clean distribution, which can be too restrictive for real-world scenarios.

BIG-bench Machine Learning Learning Theory +1

Collaborative Generative Hashing for Marketing and Fast Cold-start Recommendation

no code implementations2 Nov 2020 Yan Zhang, Ivor W. Tsang, Lixin Duan

Cold-start has being a critical issue in recommender systems with the explosion of data in e-commerce.

Marketing Recommendation Systems

Deep Pairwise Hashing for Cold-start Recommendation

no code implementations2 Nov 2020 Yan Zhang, Ivor W. Tsang, Hongzhi Yin, Guowu Yang, Defu Lian, Jingjing Li

Specifically, we first pre-train robust item representation from item content data by a Denoising Auto-encoder instead of other deterministic deep learning frameworks; then we finetune the entire framework by adding a pairwise loss objective with discrete constraints; moreover, DPH aims to minimize a pairwise ranking loss that is consistent with the ultimate goal of recommendation.

Denoising

Subgroup-based Rank-1 Lattice Quasi-Monte Carlo

no code implementations NeurIPS 2020 Yueming Lyu, Yuan Yuan, Ivor W. Tsang

We theoretically prove a lower and an upper bound of the minimum pairwise distance of any non-degenerate rank-1 lattice.

Bayesian Inference

Graph Cross Networks with Vertex Infomax Pooling

2 code implementations NeurIPS 2020 Maosen Li, Siheng Chen, Ya zhang, Ivor W. Tsang

Based on trainable hierarchical representations of a graph, GXN enables the interchange of intermediate features across scales to promote information flow.

General Classification Graph Classification

Deep N-ary Error Correcting Output Codes

1 code implementation22 Sep 2020 Hao Zhang, Joey Tianyi Zhou, Tianying Wang, Ivor W. Tsang, Rick Siow Mong Goh

To facilitate the training of N-ary ECOC with deep learning base learners, we further propose three different variants of parameter sharing architectures for deep N-ary ECOC.

Ensemble Learning General Classification +3

Intrinsic Reward Driven Imitation Learning via Generative Model

1 code implementation ICML 2020 Xingrui Yu, Yueming Lyu, Ivor W. Tsang

Thus, our module provides the imitation agent both the intrinsic intention of the demonstrator and a better exploration ability, which is critical for the agent to outperform the demonstrator.

Atari Games Imitation Learning +1

Multi-view Alignment and Generation in CCA via Consistent Latent Encoding

no code implementations24 May 2020 Yaxin Shi, Yuangang Pan, Donna Xu, Ivor W. Tsang

Multi-view alignment, achieving one-to-one correspondence of multi-view inputs, is critical in many real-world multi-view applications, especially for cross-view data analysis problems.

Secure Metric Learning via Differential Pairwise Privacy

no code implementations30 Mar 2020 Jing Li, Yuangang Pan, Yulei Sui, Ivor W. Tsang

This paper studies, for the first time, how pairwise information can be leaked to attackers during distance metric learning, and develops differential pairwise privacy (DPP), generalizing the definition of standard differential privacy, for secure metric learning.

Metric Learning

Face Hallucination with Finishing Touches

no code implementations9 Feb 2020 Yang Zhang, Ivor W. Tsang, Jun Li, Ping Liu, Xiaobo Lu, Xin Yu

The coarse-level FHnet generates a frontal coarse HR face and then the fine-level FHnet makes use of the facial component appearance prior, i. e., fine-grained facial components, to attain a frontal HR face image with authentic details.

Face Hallucination Face Recognition +2

Towards Sharper First-Order Adversary with Quantized Gradients

1 code implementation1 Feb 2020 Zhuanghua Liu, Ivor W. Tsang

However, in state-of-the-art first-order attacks, adversarial examples with sign gradients retain the sign information of each gradient component but discard the relative magnitude between components.

Adversarial Robustness Quantization

Black-box Optimizer with Implicit Natural Gradient

no code implementations9 Oct 2019 Yueming Lyu, Ivor W. Tsang

Empirically, our method with full matrix update achieves competitive performance compared with one of the state-of-the-art method CMA-ES on benchmark test problems.

Reinforcement Learning (RL)

Improving Generalization via Attribute Selection on Out-of-the-box Data

no code implementations26 Jul 2019 Xiaofeng Xu, Ivor W. Tsang, Chuancai Liu

Unfortunately, previous attribute selection methods are conducted based on the seen data, and their selected attributes have poor generalization capability to the unseen data, which is unavailable in the training stage of ZSL tasks.

Attribute Zero-Shot Learning

Node Attribute Generation on Graphs

3 code implementations23 Jul 2019 Xu Chen, Siheng Chen, Huangjie Zheng, Jiangchao Yao, Kenan Cui, Ya zhang, Ivor W. Tsang

NANG learns a unifying latent representation which is shared by both node attributes and graph structures and can be translated to different modalities.

Attribute Data Augmentation +3

Latent Adversarial Defence with Boundary-guided Generation

no code implementations16 Jul 2019 Xiaowei Zhou, Ivor W. Tsang, Jie Yin

The proposed LAD method improves the robustness of a DNN model through adversarial training on generated adversarial examples.

Fast and Robust Rank Aggregation against Model Misspecification

1 code implementation29 May 2019 Yuangang Pan, WeiJie Chen, Gang Niu, Ivor W. Tsang, Masashi Sugiyama

Specifically, the properties of our CoarsenRank are summarized as follows: (1) CoarsenRank is designed for mild model misspecification, which assumes there exist the ideal preferences (consistent with model assumption) that locates in a neighborhood of the actual preferences.

Bayesian Inference

Efficient Batch Black-box Optimization with Deterministic Regret Bounds

no code implementations24 May 2019 Yueming Lyu, Yuan Yuan, Ivor W. Tsang

In this work, we investigate black-box optimization from the perspective of frequentist kernel methods.

Bayesian Optimization

Learning Image-Specific Attributes by Hyperbolic Neighborhood Graph Propagation

no code implementations20 May 2019 Xiaofeng Xu, Ivor W. Tsang, Xiaofeng Cao, Ruiheng Zhang, Chuancai Liu

In most of existing attribute-based research, class-specific attributes (CSA), which are class-level annotations, are usually adopted due to its low annotation cost for each class instead of each individual image.

Attribute Diversity

Mental Fatigue Monitoring using Brain Dynamics Preferences

no code implementations ICLR 2019 Yuangang Pan, Avinash K Singh, Ivor W. Tsang, Chin-Teng Lin

Furthermore, a transition matrix is introduced to characterize the reliability of each channel used in EEG data, which helps in learning brain dynamics preferences only from informative EEG channels.

EEG Ordinal Classification +1

Safeguarded Dynamic Label Regression for Generalized Noisy Supervision

1 code implementation6 Mar 2019 Jiangchao Yao, Ya zhang, Ivor W. Tsang, Jun Sun

We further generalize LCCN for open-set noisy labels and the semi-supervised setting.

Ranked #35 on Image Classification on Clothing1M (using extra training data)

Learning with noisy labels regression

A Survey on Multi-output Learning

no code implementations2 Jan 2019 Donna Xu, Yaxin Shi, Ivor W. Tsang, Yew-Soon Ong, Chen Gong, Xiaobo Shen

Multi-output learning aims to simultaneously predict multiple outputs given an input.

Decision Making

Privacy-preserving Stochastic Gradual Learning

no code implementations30 Sep 2018 Bo Han, Ivor W. Tsang, Xiaokui Xiao, Ling Chen, Sai-fu Fung, Celina P. Yu

PRESTIGE bridges private updates of the primal variable (by private sampling) with the gradual curriculum learning (CL).

Privacy Preserving Stochastic Optimization

Target-Independent Active Learning via Distribution-Splitting

no code implementations28 Sep 2018 Xiaofeng Cao, Ivor W. Tsang, Xiaofeng Xu, Guandong Xu

By discovering the connections between hypothesis and input distribution, we map the volume of version space into the number density and propose a target-independent distribution-splitting strategy with the following advantages: 1) provide theoretical guarantees on reducing label complexity and error rate as volume-splitting; 2) break the curse of initial hypothesis; 3) provide model guidance for a target-independent AL algorithm in real AL tasks.

Active Learning

XAI Beyond Classification: Interpretable Neural Clustering

no code implementations22 Aug 2018 Xi Peng, Yunnan Li, Ivor W. Tsang, Hongyuan Zhu, Jiancheng Lv, Joey Tianyi Zhou

The second is implementing discrete $k$-means with a differentiable neural network that embraces the advantages of parallel computing, online clustering, and clustering-favorable representation learning.

Classification Clustering +3

A Structured Perspective of Volumes on Active Learning

no code implementations24 Jul 2018 Xiaofeng Cao, Ivor W. Tsang, Guandong Xu

In this paper, we approximate the version space to a structured {hypersphere} that covers most of the hypotheses, and then divide the available AL sampling approaches into two kinds of strategies: Outer Volume Sampling and Inner Volume Sampling.

Active Learning

Understanding VAEs in Fisher-Shannon Plane

no code implementations10 Jul 2018 Huangjie Zheng, Jiangchao Yao, Ya zhang, Ivor W. Tsang, Jia Wang

In information theory, Fisher information and Shannon information (entropy) are respectively used to quantify the uncertainty associated with the distribution modeling and the uncertainty in specifying the outcome of given variables.

Decoder Representation Learning

Matrix Co-completion for Multi-label Classification with Missing Features and Labels

no code implementations23 May 2018 Miao Xu, Gang Niu, Bo Han, Ivor W. Tsang, Zhi-Hua Zhou, Masashi Sugiyama

We consider a challenging multi-label classification problem where both feature matrix $\X$ and label matrix $\Y$ have missing entries.

General Classification Matrix Completion +1

Label Embedding with Partial Heterogeneous Contexts

no code implementations3 May 2018 Yaxin Shi, Donna Xu, Yuangang Pan, Ivor W. Tsang, Shirui Pan

In this paper, we propose a general Partial Heterogeneous Context Label Embedding (PHCLE) framework to address these challenges.

Descriptive Image Classification

Complementary Attributes: A New Clue to Zero-Shot Learning

no code implementations17 Apr 2018 Xiaofeng Xu, Ivor W. Tsang, Chuancai Liu

Extensive experiments on five ZSL benchmark datasets and the large-scale ImageNet dataset demonstrate that the proposed complementary attributes and rank aggregation can significantly and robustly improve existing ZSL methods and achieve the state-of-the-art performance.

Attribute Style Generalization +1

VR-SGD: A Simple Stochastic Variance Reduction Method for Machine Learning

1 code implementation26 Feb 2018 Fanhua Shang, Kaiwen Zhou, Hongying Liu, James Cheng, Ivor W. Tsang, Lijun Zhang, DaCheng Tao, Licheng Jiao

In this paper, we propose a simple variant of the original SVRG, called variance reduced stochastic gradient descent (VR-SGD).

BIG-bench Machine Learning

Degeneration in VAE: in the Light of Fisher Information Loss

no code implementations19 Feb 2018 Huangjie Zheng, Jiangchao Yao, Ya zhang, Ivor W. Tsang

While enormous progress has been made to Variational Autoencoder (VAE) in recent years, similar to other deep networks, VAE with deep networks suffers from the problem of degeneration, which seriously weakens the correlation between the input and the corresponding latent codes, deviating from the goal of the representation learning.

Representation Learning

Online Product Quantization

no code implementations29 Nov 2017 Donna Xu, Ivor W. Tsang, Ying Zhang

The experiments demonstrate that our online PQ model is both time-efficient and effective for ANN search in dynamic large scale databases compared with baseline methods and the idea of partial PQ codebook update further reduces the update cost.

Quantization

Transfer Hashing with Privileged Information

no code implementations13 May 2016 Joey Tianyi Zhou, Xinxing Xu, Sinno Jialin Pan, Ivor W. Tsang, Zheng Qin, Rick Siow Mong Goh

Specifically, we extend the standard learning to hash method, Iterative Quantization (ITQ), in a transfer learning manner, namely ITQ+.

Quantization Transfer Learning

On the Convergence of A Family of Robust Losses for Stochastic Gradient Descent

no code implementations5 May 2016 Bo Han, Ivor W. Tsang, Ling Chen

The convergence of Stochastic Gradient Descent (SGD) using convex loss functions has been widely studied.

N-ary Error Correcting Coding Scheme

no code implementations18 Mar 2016 Joey Tianyi Zhou, Ivor W. Tsang, Shen-Shyang Ho, Klaus-Robert Muller

The coding matrix design plays a fundamental role in the prediction performance of the error correcting output codes (ECOC)-based multi-class task.

Classification General Classification

A Novel Regularized Principal Graph Learning Framework on Explicit Graph Representation

no code implementations9 Dec 2015 Qi Mao, Li Wang, Ivor W. Tsang, Yijun Sun

As showcases, models that can learn a spanning tree or a weighted undirected $\ell_1$ graph are proposed, and a new learning algorithm is developed that learns a set of principal points and a graph structure from data, simultaneously.

Graph Embedding Graph Learning

Event Detection using Multi-Level Relevance Labels and Multiple Features

no code implementations CVPR 2014 Zhongwen Xu, Ivor W. Tsang, Yi Yang, Zhigang Ma, Alexander G. Hauptmann

We address the challenging problem of utilizing related exemplars for complex event detection while multiple features are available.

Event Detection

Convex and Scalable Weakly Labeled SVMs

no code implementations6 Mar 2013 Yu-Feng Li, Ivor W. Tsang, James T. Kwok, Zhi-Hua Zhou

In this paper, we study the problem of learning from weakly labeled data, where labels of the training examples are incomplete.

Clustering Information Retrieval +1

Matching Pursuit LASSO Part II: Applications and Sparse Recovery over Batch Signals

no code implementations20 Feb 2013 Mingkui Tan, Ivor W. Tsang, Li Wang

Matching Pursuit LASSIn Part I \cite{TanPMLPart1}, a Matching Pursuit LASSO ({MPL}) algorithm has been presented for solving large-scale sparse recovery (SR) problems.

Compressive Sensing Face Recognition

Towards Ultrahigh Dimensional Feature Selection for Big Data

no code implementations24 Sep 2012 Mingkui Tan, Ivor W. Tsang, Li Wang

In this paper, we present a new adaptive feature scaling scheme for ultrahigh-dimensional feature selection on Big Data.

feature selection Selection bias

A Feature Selection Method for Multivariate Performance Measures

no code implementations5 Mar 2011 Qi Mao, Ivor W. Tsang

The analyses by comparing with the state-of-the-art feature selection methods show that the proposed method is superior to others.

feature selection General Classification +5

Efficient Multi-Template Learning for Structured Prediction

no code implementations4 Mar 2011 Qi Mao, Ivor W. Tsang

To alleviate this issue, in this paper, we propose a novel multiple template learning paradigm to learn structured prediction and the importance of each template simultaneously, so that hundreds of arbitrary templates could be added into the learning model without caution.

Dependency Parsing Structured Prediction

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