Search Results for author: Dejing Dou

Found 122 papers, 48 papers with code

Parameter-Efficient Domain Knowledge Integration from Multiple Sources for Biomedical Pre-trained Language Models

no code implementations Findings (EMNLP) 2021 Qiuhao Lu, Dejing Dou, Thien Huu Nguyen

These knowledge adapters are pre-trained for individual domain knowledge sources and integrated via an attention-based knowledge controller to enrich PLMs.

Self-Supervised Learning

Scalable Differential Privacy with Certified Robustness in Adversarial Learning

1 code implementation ICML 2020 Hai Phan, My T. Thai, Han Hu, Ruoming Jin, Tong Sun, Dejing Dou

In this paper, we aim to develop a scalable algorithm to preserve differential privacy (DP) in adversarial learning for deep neural networks (DNNs), with certified robustness to adversarial examples.

Dual-space Hierarchical Learning for Goal-guided Conversational Recommendation

1 code implementation30 Dec 2023 Can Chen, Hao liu, Zeming Liu, Xue Liu, Dejing Dou

In this paper, we propose Dual-space Hierarchical Learning (DHL) to leverage multi-level goal sequences and their hierarchical relationships for conversational recommendation.

Recommendation Systems Representation Learning

Efficient Asynchronous Federated Learning with Sparsification and Quantization

no code implementations23 Dec 2023 Juncheng Jia, Ji Liu, Chendi Zhou, Hao Tian, Mianxiong Dong, Dejing Dou

As the bandwidth between the devices and the server is relatively low, the communication of intermediate data becomes a bottleneck.

Federated Learning Quantization

AEDFL: Efficient Asynchronous Decentralized Federated Learning with Heterogeneous Devices

no code implementations18 Dec 2023 Ji Liu, Tianshi Che, Yang Zhou, Ruoming Jin, Huaiyu Dai, Dejing Dou, Patrick Valduriez

First, we propose an asynchronous FL system model with an efficient model aggregation method for improving the FL convergence.

Federated Learning

On Mask-based Image Set Desensitization with Recognition Support

no code implementations14 Dec 2023 Qilong Li, Ji Liu, Yifan Sun, Chongsheng Zhang, Dejing Dou

In addition, we propose a feature selection masknet as the model adjustment method to improve the performance based on the masked images.

feature selection

Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization

1 code implementation23 Oct 2023 Tianshi Che, Ji Liu, Yang Zhou, Jiaxiang Ren, Jiwen Zhou, Victor S. Sheng, Huaiyu Dai, Dejing Dou

This paper proposes a Parameter-efficient prompt Tuning approach with Adaptive Optimization, i. e., FedPepTAO, to enable efficient and effective FL of LLMs.

Federated Learning

MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts

no code implementations3 Oct 2023 Weibin Liao, Haoyi Xiong, Qingzhong Wang, Yan Mo, Xuhong LI, Yi Liu, Zeyu Chen, Siyu Huang, Dejing Dou

In this work, we study a novel self-supervised pre-training pipeline, namely Multi-task Self-super-vised Continual Learning (MUSCLE), for multiple medical imaging tasks, such as classification and segmentation, using X-ray images collected from multiple body parts, including heads, lungs, and bones.

Continual Learning Representation Learning +1

ColdNAS: Search to Modulate for User Cold-Start Recommendation

1 code implementation6 Jun 2023 Shiguang Wu, Yaqing Wang, Qinghe Jing, daxiang dong, Dejing Dou, Quanming Yao

Instead of using a fixed modulation function and deciding modulation position by expertise, we propose a modulation framework called ColdNAS for user cold-start problem, where we look for proper modulation structure, including function and position, via neural architecture search.

Neural Architecture Search Position +1

Robust Cross-Modal Knowledge Distillation for Unconstrained Videos

1 code implementation16 Apr 2023 Wenke Xia, Xingjian Li, Andong Deng, Haoyi Xiong, Dejing Dou, Di Hu

However, such semantic consistency from the synchronization is hard to guarantee in unconstrained videos, due to the irrelevant modality noise and differentiated semantic correlation.

Action Recognition Audio Tagging +3

Spectral Enhanced Rectangle Transformer for Hyperspectral Image Denoising

1 code implementation CVPR 2023 Miaoyu Li, Ji Liu, Ying Fu, Yulun Zhang, Dejing Dou

In this paper, we address these issues by proposing a spectral enhanced rectangle Transformer, driving it to explore the non-local spatial similarity and global spectral low-rank property of HSIs.

Hyperspectral Image Denoising Image Denoising

Doubly Stochastic Models: Learning with Unbiased Label Noises and Inference Stability

no code implementations1 Apr 2023 Haoyi Xiong, Xuhong LI, Boyang Yu, Zhanxing Zhu, Dongrui Wu, Dejing Dou

While previous studies primarily focus on the affects of label noises to the performance of learning, our work intends to investigate the implicit regularization effects of the label noises, under mini-batch sampling settings of stochastic gradient descent (SGD), with assumptions that label noises are unbiased.

Video4MRI: An Empirical Study on Brain Magnetic Resonance Image Analytics with CNN-based Video Classification Frameworks

no code implementations24 Feb 2023 Yuxuan Zhang, Qingzhong Wang, Jiang Bian, Yi Liu, Yanwu Xu, Dejing Dou, Haoyi Xiong

Due to the high similarity between MRI data and videos, we conduct extensive empirical studies on video recognition techniques for MRI classification to answer the questions: (1) can we directly use video recognition models for MRI classification, (2) which model is more appropriate for MRI, (3) are the common tricks like data augmentation in video recognition still useful for MRI classification?

Classification Data Augmentation +3

Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement

1 code implementation8 Jan 2023 Yan Li, Xinjiang Lu, Yaqing Wang, Dejing Dou

In this work, we propose to address the time series forecasting problem with generative modeling and propose a bidirectional variational auto-encoder (BVAE) equipped with diffusion, denoise, and disentanglement, namely D3VAE.

Denoising Disentanglement +2

Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution

1 code implementation5 Jan 2023 Yan Li, Xinjiang Lu, Haoyi Xiong, Jian Tang, Jiantao Su, Bo Jin, Dejing Dou

Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning.

Time Series Time Series Forecasting +1

Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approach

1 code implementation5 Jan 2023 Miao Chen, Xinjiang Lu, Tong Xu, Yanyan Li, Jingbo Zhou, Dejing Dou, Hui Xiong

Although remarkable progress on the neural table-to-text methods has been made, the generalization issues hinder the applicability of these models due to the limited source tables.

Descriptive Language Modelling +1

Temporal Output Discrepancy for Loss Estimation-based Active Learning

no code implementations20 Dec 2022 Siyu Huang, Tianyang Wang, Haoyi Xiong, Bihan Wen, Jun Huan, Dejing Dou

Inspired by the fact that the samples with higher loss are usually more informative to the model than the samples with lower loss, in this paper we present a novel deep active learning approach that queries the oracle for data annotation when the unlabeled sample is believed to incorporate high loss.

Active Learning Image Classification +1

Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Features

1 code implementation19 Dec 2022 Qingrui Jia, Xuhong LI, Lei Yu, Jiang Bian, Penghao Zhao, Shupeng Li, Haoyi Xiong, Dejing Dou

While mislabeled or ambiguously-labeled samples in the training set could negatively affect the performance of deep models, diagnosing the dataset and identifying mislabeled samples helps to improve the generalization power.

A Contextual Master-Slave Framework on Urban Region Graph for Urban Village Detection

no code implementations26 Nov 2022 Congxi Xiao, Jingbo Zhou, Jizhou Huang, HengShu Zhu, Tong Xu, Dejing Dou, Hui Xiong

The core idea of such a framework is to firstly pre-train a basis (or master) model over the URG, and then to adaptively derive specific (or slave) models from the basis model for different regions.

Specificity

Multi-Job Intelligent Scheduling with Cross-Device Federated Learning

no code implementations24 Nov 2022 Ji Liu, Juncheng Jia, Beichen Ma, Chendi Zhou, Jingbo Zhou, Yang Zhou, Huaiyu Dai, Dejing Dou

The system model enables a parallel training process of multiple jobs, with a cost model based on the data fairness and the training time of diverse devices during the parallel training process.

Bayesian Optimization Fairness +2

Textual Data Augmentation for Patient Outcomes Prediction

no code implementations13 Nov 2022 Qiuhao Lu, Dejing Dou, Thien Huu Nguyen

Deep learning models have demonstrated superior performance in various healthcare applications.

Data Augmentation Language Modelling

SDWPF: A Dataset for Spatial Dynamic Wind Power Forecasting Challenge at KDD Cup 2022

1 code implementation8 Aug 2022 Jingbo Zhou, Xinjiang Lu, Yixiong Xiao, Jiantao Su, Junfu Lyu, Yanjun Ma, Dejing Dou

Thus, Wind Power Forecasting (WPF) has been widely recognized as one of the most critical issues in wind power integration and operation.

$\textbf{P$^2$A}$: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos

no code implementations26 Jul 2022 Jiang Bian, Qingzhong Wang, Haoyi Xiong, Jun Huang, Chen Liu, Xuhong LI, Jun Cheng, Jun Zhao, Feixiang Lu, Dejing Dou

While deep learning has been widely used for video analytics, such as video classification and action detection, dense action detection with fast-moving subjects from sports videos is still challenging.

Action Detection Action Localization +2

Large-scale Knowledge Distillation with Elastic Heterogeneous Computing Resources

1 code implementation14 Jul 2022 Ji Liu, daxiang dong, Xi Wang, An Qin, Xingjian Li, Patrick Valduriez, Dejing Dou, dianhai yu

Although more layers and more parameters generally improve the accuracy of the models, such big models generally have high computational complexity and require big memory, which exceed the capacity of small devices for inference and incurs long training time.

Knowledge Distillation

Accelerated Federated Learning with Decoupled Adaptive Optimization

no code implementations14 Jul 2022 Jiayin Jin, Jiaxiang Ren, Yang Zhou, Lingjuan Lyu, Ji Liu, Dejing Dou

The federated learning (FL) framework enables edge clients to collaboratively learn a shared inference model while keeping privacy of training data on clients.

Federated Learning

Distilling Ensemble of Explanations for Weakly-Supervised Pre-Training of Image Segmentation Models

2 code implementations4 Jul 2022 Xuhong LI, Haoyi Xiong, Yi Liu, Dingfu Zhou, Zeyu Chen, Yaqing Wang, Dejing Dou

Though image classification datasets could provide the backbone networks with rich visual features and discriminative ability, they are incapable of fully pre-training the target model (i. e., backbone+segmentation modules) in an end-to-end manner.

Classification Image Classification +3

Pareto Optimization for Active Learning under Out-of-Distribution Data Scenarios

no code implementations4 Jul 2022 Xueying Zhan, Zeyu Dai, Qingzhong Wang, Qing Li, Haoyi Xiong, Dejing Dou, Antoni B. Chan

In this paper, we propose a sampling scheme, Monte-Carlo Pareto Optimization for Active Learning (POAL), which selects optimal subsets of unlabeled samples with fixed batch size from the unlabeled data pool.

Active Learning

FedHiSyn: A Hierarchical Synchronous Federated Learning Framework for Resource and Data Heterogeneity

no code implementations21 Jun 2022 Guanghao Li, Yue Hu, Miao Zhang, Ji Liu, Quanjun Yin, Yong Peng, Dejing Dou

As the efficiency of training in the ring topology prefers devices with homogeneous resources, the classification based on the computing capacity mitigates the impact of straggler effects.

Federated Learning

Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularization

no code implementations12 Jun 2022 Hang Hua, Xingjian Li, Dejing Dou, Cheng-Zhong Xu, Jiebo Luo

The advent of large-scale pre-trained language models has contributed greatly to the recent progress in natural language processing.

Domain Generalization Language Modelling +3

A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications

1 code implementation2 Jun 2022 Fei Wu, Qingzhong Wang, Jian Bian, Haoyi Xiong, Ning Ding, Feixiang Lu, Jun Cheng, Dejing Dou

Finally, we discuss the challenges and unsolved problems in this area and to facilitate sports analytics, we develop a toolbox using PaddlePaddle, which supports football, basketball, table tennis and figure skating action recognition.

Action Recognition Sports Analytics +1

Feature Forgetting in Continual Representation Learning

no code implementations26 May 2022 Xiao Zhang, Dejing Dou, Ji Wu

To study the feature forgetting problem, we create a synthetic dataset to identify and visualize the prevalence of feature forgetting in neural networks.

Continual Learning Representation Learning

A Simple yet Effective Framework for Active Learning to Rank

no code implementations20 May 2022 Qingzhong Wang, Haifang Li, Haoyi Xiong, Wen Wang, Jiang Bian, Yu Lu, Shuaiqiang Wang, Zhicong Cheng, Dejing Dou, Dawei Yin

To handle the diverse query requests from users at web-scale, Baidu has done tremendous efforts in understanding users' queries, retrieve relevant contents from a pool of trillions of webpages, and rank the most relevant webpages on the top of results.

Active Learning Learning-To-Rank

FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Server

no code implementations25 Apr 2022 Hong Zhang, Ji Liu, Juncheng Jia, Yang Zhou, Huaiyu Dai, Dejing Dou

Despite achieving remarkable performance, Federated Learning (FL) suffers from two critical challenges, i. e., limited computational resources and low training efficiency.

Federated Learning

Structure-aware Protein Self-supervised Learning

1 code implementation6 Apr 2022 Can Chen, Jingbo Zhou, Fan Wang, Xue Liu, Dejing Dou

Furthermore, we propose to leverage the available protein language model pretrained on protein sequences to enhance the self-supervised learning.

Protein Language Model Representation Learning +1

A Comparative Survey of Deep Active Learning

1 code implementation25 Mar 2022 Xueying Zhan, Qingzhong Wang, Kuan-Hao Huang, Haoyi Xiong, Dejing Dou, Antoni B. Chan

In this work, We construct a DAL toolkit, DeepAL+, by re-implementing 19 highly-cited DAL methods.

Active Learning

Learning Moving-Object Tracking with FMCW LiDAR

no code implementations2 Mar 2022 Yi Gu, Hongzhi Cheng, Kafeng Wang, Dejing Dou, Chengzhong Xu, Hui Kong

In this paper, we propose a learning-based moving-object tracking method utilizing our newly developed LiDAR sensor, Frequency Modulated Continuous Wave (FMCW) LiDAR.

Contrastive Learning Object +1

Validating the Lottery Ticket Hypothesis with Inertial Manifold Theory

no code implementations NeurIPS 2021 Zeru Zhang, Jiayin Jin, Zijie Zhang, Yang Zhou, Xin Zhao, Jiaxiang Ren, Ji Liu, Lingfei Wu, Ruoming Jin, Dejing Dou

Despite achieving remarkable efficiency, traditional network pruning techniques often follow manually-crafted heuristics to generate pruned sparse networks.

Network Pruning

Generalized DataWeighting via Class-Level Gradient Manipulation

1 code implementation NeurIPS 2021 Can Chen, Shuhao Zheng, Xi Chen, Erqun Dong, Xue (Steve) Liu, Hao liu, Dejing Dou

To be specific, GDW unrolls the loss gradient to class-level gradients by the chain rule and reweights the flow of each gradient separately.

Generalized Data Weighting via Class-level Gradient Manipulation

1 code implementation29 Oct 2021 Can Chen, Shuhao Zheng, Xi Chen, Erqun Dong, Xue Liu, Hao liu, Dejing Dou

To be specific, GDW unrolls the loss gradient to class-level gradients by the chain rule and reweights the flow of each gradient separately.

SenseMag: Enabling Low-Cost Traffic Monitoring using Non-invasive Magnetic Sensing

no code implementations24 Oct 2021 Kafeng Wang, Haoyi Xiong, Jie Zhang, Hongyang Chen, Dejing Dou, Cheng-Zhong Xu

Extensive experiment based on real-word field deployment (on the highways in Shenzhen, China) shows that SenseMag significantly outperforms the existing methods in both classification accuracy and the granularity of vehicle types (i. e., 7 types by SenseMag versus 4 types by the existing work in comparisons).

Management

AgFlow: Fast Model Selection of Penalized PCA via Implicit Regularization Effects of Gradient Flow

no code implementations7 Oct 2021 Haiyan Jiang, Haoyi Xiong, Dongrui Wu, Ji Liu, Dejing Dou

Principal component analysis (PCA) has been widely used as an effective technique for feature extraction and dimension reduction.

Dimensionality Reduction Model Selection

Exploring the Common Principal Subspace of Deep Features in Neural Networks

no code implementations6 Oct 2021 Haoran Liu, Haoyi Xiong, Yaqing Wang, Haozhe An, Dongrui Wu, Dejing Dou

Specifically, we design a new metric $\mathcal{P}$-vector to represent the principal subspace of deep features learned in a DNN, and propose to measure angles between the principal subspaces using $\mathcal{P}$-vectors.

Image Reconstruction Self-Supervised Learning

GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction

1 code implementation24 Sep 2021 Shuangli Li, Jingbo Zhou, Tong Xu, Dejing Dou, Hui Xiong

Though graph contrastive learning (GCL) methods have achieved extraordinary performance with insufficient labeled data, most focused on designing data augmentation schemes for general graphs.

Contrastive Learning Data Augmentation +4

Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Study

no code implementations2 Sep 2021 Xuhong LI, Haoyi Xiong, Siyu Huang, Shilei Ji, Dejing Dou

Existing interpretation algorithms have found that, even deep models make the same and right predictions on the same image, they might rely on different sets of input features for classification.

Attribute Image Classification +2

Semi-Supervised Active Learning with Temporal Output Discrepancy

1 code implementation ICCV 2021 Siyu Huang, Tianyang Wang, Haoyi Xiong, Jun Huan, Dejing Dou

To lower the cost of data annotation, active learning has been proposed to interactively query an oracle to annotate a small proportion of informative samples in an unlabeled dataset.

Active Learning Image Classification +1

Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinity

1 code implementation21 Jul 2021 Shuangli Li, Jingbo Zhou, Tong Xu, Liang Huang, Fan Wang, Haoyi Xiong, Weili Huang, Dejing Dou, Hui Xiong

To this end, we propose a structure-aware interactive graph neural network (SIGN) which consists of two components: polar-inspired graph attention layers (PGAL) and pairwise interactive pooling (PiPool).

Drug Discovery Graph Attention +1

MugRep: A Multi-Task Hierarchical Graph Representation Learning Framework for Real Estate Appraisal

no code implementations12 Jul 2021 Weijia Zhang, Hao liu, Lijun Zha, HengShu Zhu, Ji Liu, Dejing Dou, Hui Xiong

Real estate appraisal refers to the process of developing an unbiased opinion for real property's market value, which plays a vital role in decision-making for various players in the marketplace (e. g., real estate agents, appraisers, lenders, and buyers).

Decision Making Graph Representation Learning +1

From Personalized Medicine to Population Health: A Survey of mHealth Sensing Techniques

no code implementations2 Jul 2021 Zhiyuan Wang, Haoyi Xiong, Jie Zhang, Sijia Yang, Mehdi Boukhechba, Laura E. Barnes, Daqing Zhang, Dejing Dou

Mobile Sensing Apps have been widely used as a practical approach to collect behavioral and health-related information from individuals and provide timely intervention to promote health and well-beings, such as mental health and chronic cares.

Robust Matrix Factorization with Grouping Effect

no code implementations25 Jun 2021 Haiyan Jiang, Shuyu Li, Luwei Zhang, Haoyi Xiong, Dejing Dou

Compared with existing algorithms, the proposed GRMF can automatically learn the grouping structure and sparsity in MF without prior knowledge, by introducing a naturally adjustable non-convex regularization to achieve simultaneous sparsity and grouping effect.

Denoising

Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples

no code implementations20 Jun 2021 Xuanyu Wu, Xuhong LI, Haoyi Xiong, Xiao Zhang, Siyu Huang, Dejing Dou

Incorporating with a set of randomized strategies for well-designed data transformations over the training set, ContRE adopts classification errors and Fisher ratios on the generated contrastive examples to assess and analyze the generalization performance of deep models in complement with a testing set.

Contrastive Learning

JIZHI: A Fast and Cost-Effective Model-As-A-Service System for Web-Scale Online Inference at Baidu

1 code implementation3 Jun 2021 Hao liu, Qian Gao, Jiang Li, Xiaochao Liao, Hao Xiong, Guangxing Chen, Wenlin Wang, Guobao Yang, Zhiwei Zha, daxiang dong, Dejing Dou, Haoyi Xiong

In this work, we present JIZHI - a Model-as-a-Service system - that per second handles hundreds of millions of online inference requests to huge deep models with more than trillions of sparse parameters, for over twenty real-time recommendation services at Baidu, Inc.

Recommendation Systems

From Distributed Machine Learning to Federated Learning: A Survey

no code implementations29 Apr 2021 Ji Liu, Jizhou Huang, Yang Zhou, Xuhong LI, Shilei Ji, Haoyi Xiong, Dejing Dou

Because of laws or regulations, the distributed data and computing resources cannot be directly shared among different regions or organizations for machine learning tasks.

BIG-bench Machine Learning Federated Learning

Cross-lingual Entity Alignment with Adversarial Kernel Embedding and Adversarial Knowledge Translation

1 code implementation16 Apr 2021 Gong Zhang, Yang Zhou, Sixing Wu, Zeru Zhang, Dejing Dou

With the guidance of known aligned entities in the context of multiple random walks, an adversarial knowledge translation model is developed to fill and translate masked entities in pairwise random walks from two KGs.

Attribute Entity Alignment +2

Semantic Oppositeness Assisted Deep Contextual Modeling for Automatic Rumor Detection in Social Networks

no code implementations EACL 2021 Nisansa de Silva, Dejing Dou

Social networks face a major challenge in the form of rumors and fake news, due to their intrinsic nature of connecting users to millions of others, and of giving any individual the power to post anything.

Semantic Similarity Semantic Textual Similarity

ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows

1 code implementation CVPR 2021 Jie An, Siyu Huang, Yibing Song, Dejing Dou, Wei Liu, Jiebo Luo

The forward inference projects input images into deep features, while the backward inference remaps deep features back to input images in a lossless and unbiased way.

Style Transfer

SMILE: Self-Distilled MIxup for Efficient Transfer LEarning

no code implementations25 Mar 2021 Xingjian Li, Haoyi Xiong, Chengzhong Xu, Dejing Dou

Performing mixup for transfer learning with pre-trained models however is not that simple, a high capacity pre-trained model with a large fully-connected (FC) layer could easily overfit to the target dataset even with samples-to-labels mixed up.

Transfer Learning

Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond

1 code implementation19 Mar 2021 Xuhong LI, Haoyi Xiong, Xingjian Li, Xuanyu Wu, Xiao Zhang, Ji Liu, Jiang Bian, Dejing Dou

Then, to understand the interpretation results, we also survey the performance metrics for evaluating interpretation algorithms.

Adversarial Robustness

Adaptive Consistency Regularization for Semi-Supervised Transfer Learning

1 code implementation CVPR 2021 Abulikemu Abuduweili, Xingjian Li, Humphrey Shi, Cheng-Zhong Xu, Dejing Dou

To better exploit the value of both pre-trained weights and unlabeled target examples, we introduce adaptive consistency regularization that consists of two complementary components: Adaptive Knowledge Consistency (AKC) on the examples between the source and target model, and Adaptive Representation Consistency (ARC) on the target model between labeled and unlabeled examples.

Pseudo Label Transfer Learning

Intelligent Electric Vehicle Charging Recommendation Based on Multi-Agent Reinforcement Learning

1 code implementation15 Feb 2021 Weijia Zhang, Hao liu, Fan Wang, Tong Xu, Haoran Xin, Dejing Dou, Hui Xiong

Electric Vehicle (EV) has become a preferable choice in the modern transportation system due to its environmental and energy sustainability.

Multi-agent Reinforcement Learning reinforcement-learning +1

Out-of-Town Recommendation with Travel Intention Modeling

1 code implementation29 Jan 2021 Haoran Xin, Xinjiang Lu, Tong Xu, Hao liu, Jingjing Gu, Dejing Dou, Hui Xiong

Second, a user-specific travel intention is formulated as an aggregation combining home-town preference and generic travel intention together, where the generic travel intention is regarded as a mixture of inherent intentions that can be learned by Neural Topic Model (NTM).

point of interests

Empirical Studies on the Convergence of Feature Spaces in Deep Learning

no code implementations1 Jan 2021 Haoran Liu, Haoyi Xiong, Yaqing Wang, Haozhe An, Dongrui Wu, Dejing Dou

While deep learning is effective to learn features/representations from data, the distributions of samples in feature spaces learned by various architectures for different training tasks (e. g., latent layers of AEs and feature vectors in CNN classifiers) have not been well-studied or compared.

Image Reconstruction Self-Supervised Learning

Can We Use Gradient Norm as a Measure of Generalization Error for Model Selection in Practice?

no code implementations1 Jan 2021 Haozhe An, Haoyi Xiong, Xuhong LI, Xingjian Li, Dejing Dou, Zhanxing Zhu

The recent theoretical investigation (Li et al., 2020) on the upper bound of generalization error of deep neural networks (DNNs) demonstrates the potential of using the gradient norm as a measure that complements validation accuracy for model selection in practice.

Model Selection

Implicit Regularization Effects of Unbiased Random Label Noises with SGD

no code implementations1 Jan 2021 Haoyi Xiong, Xuhong LI, Boyang Yu, Dejing Dou, Dongrui Wu, Zhanxing Zhu

Random label noises (or observational noises) widely exist in practical machinelearning settings.

Democratizing Evaluation of Deep Model Interpretability through Consensus

no code implementations1 Jan 2021 Xuhong LI, Haoyi Xiong, Siyu Huang, Shilei Ji, Yanjie Fu, Dejing Dou

Given any task/dataset, Consensus first obtains the interpretation results using existing tools, e. g., LIME (Ribeiro et al., 2016), for every model in the committee, then aggregates the results from the entire committee and approximates the “ground truth” of interpretations through voting.

Feature Importance

Model information as an analysis tool in deep learning

no code implementations1 Jan 2021 Xiao Zhang, Di Hu, Xingjian Li, Dejing Dou, Ji Wu

We demonstrate using model information as a general analysis tool to gain insight into problems that arise in deep learning.

Information distance for neural network functions

no code implementations1 Jan 2021 Xiao Zhang, Dejing Dou, Ji Wu

We provide a practical distance measure in the space of functions parameterized by neural networks.

Joint Air Quality and Weather Prediction Based on Multi-Adversarial Spatiotemporal Networks

no code implementations30 Dec 2020 Jindong Han, Hao liu, HengShu Zhu, Hui Xiong, Dejing Dou

Specifically, we first propose a heterogeneous recurrent graph neural network to model the spatiotemporal autocorrelation among air quality and weather monitoring stations.

Graph Learning Multi-Task Learning

C-Watcher: A Framework for Early Detection of High-Risk Neighborhoods Ahead of COVID-19 Outbreak

no code implementations22 Dec 2020 Congxi Xiao, Jingbo Zhou, Jizhou Huang, An Zhuo, Ji Liu, Haoyi Xiong, Dejing Dou

Furthermore, to transfer the firsthand knowledge (witted in epicenters) to the target city before local outbreaks, we adopt a novel adversarial encoder framework to learn "city-invariant" representations from the mobility-related features for precise early detection of high-risk neighborhoods, even before any confirmed cases known, in the target city.

Distance-aware Molecule Graph Attention Network for Drug-Target Binding Affinity Prediction

1 code implementation17 Dec 2020 Jingbo Zhou, Shuangli Li, Liang Huang, Haoyi Xiong, Fan Wang, Tong Xu, Hui Xiong, Dejing Dou

The hierarchical attentive aggregation can capture spatial dependencies among atoms, as well as fuse the position-enhanced information with the capability of discriminating multiple spatial relations among atoms.

Drug Discovery Graph Attention +2

Temporal Relational Modeling with Self-Supervision for Action Segmentation

1 code implementation14 Dec 2020 Dong Wang, Di Hu, Xingjian Li, Dejing Dou

The main reason is that large number of nodes (i. e., video frames) makes GCNs hard to capture and model temporal relations in videos.

Action Recognition Action Segmentation +1

Adversarial Attacks on Deep Graph Matching

no code implementations NeurIPS 2020 Zijie Zhang, Zeru Zhang, Yang Zhou, Yelong Shen, Ruoming Jin, Dejing Dou

Despite achieving remarkable performance, deep graph learning models, such as node classification and network embedding, suffer from harassment caused by small adversarial perturbations.

Adversarial Attack Density Estimation +5

Introducing Syntactic Structures into Target Opinion Word Extraction with Deep Learning

no code implementations EMNLP 2020 Amir Pouran Ben Veyseh, Nasim Nouri, Franck Dernoncourt, Dejing Dou, Thien Huu Nguyen

In this work, we propose to incorporate the syntactic structures of the sentences into the deep learning models for TOWE, leveraging the syntax-based opinion possibility scores and the syntactic connections between the words.

Aspect-Based Sentiment Analysis Aspect-oriented Opinion Extraction +1

Towards Accurate Knowledge Transfer via Target-awareness Representation Disentanglement

no code implementations16 Oct 2020 Xingjian Li, Di Hu, Xuhong LI, Haoyi Xiong, Zhi Ye, Zhipeng Wang, Chengzhong Xu, Dejing Dou

Fine-tuning deep neural networks pre-trained on large scale datasets is one of the most practical transfer learning paradigm given limited quantity of training samples.

Disentanglement Transfer Learning

Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching

1 code implementation NeurIPS 2020 Di Hu, Rui Qian, Minyue Jiang, Xiao Tan, Shilei Wen, Errui Ding, Weiyao Lin, Dejing Dou

First, we propose to learn robust object representations by aggregating the candidate sound localization results in the single source scenes.

Object Object Localization

Measuring Information Transfer in Neural Networks

no code implementations16 Sep 2020 Xiao Zhang, Xingjian Li, Dejing Dou, Ji Wu

We propose a practical measure of the generalizable information in a neural network model based on prequential coding, which we term Information Transfer ($L_{IT}$).

Continual Learning Transfer Learning

XMixup: Efficient Transfer Learning with Auxiliary Samples by Cross-domain Mixup

no code implementations20 Jul 2020 Xingjian Li, Haoyi Xiong, Haozhe An, Cheng-Zhong Xu, Dejing Dou

While the existing multitask learning algorithms need to run backpropagation over both the source and target datasets and usually consume a higher gradient complexity, XMixup transfers the knowledge from source to target tasks more efficiently: for every class of the target task, XMixup selects the auxiliary samples from the source dataset and augments training samples via the simple mixup strategy.

Transfer Learning

Generating Person Images with Appearance-aware Pose Stylizer

1 code implementation17 Jul 2020 Siyu Huang, Haoyi Xiong, Zhi-Qi Cheng, Qingzhong Wang, Xingran Zhou, Bihan Wen, Jun Huan, Dejing Dou

Generation of high-quality person images is challenging, due to the sophisticated entanglements among image factors, e. g., appearance, pose, foreground, background, local details, global structures, etc.

Image Generation

Representation Transfer by Optimal Transport

no code implementations13 Jul 2020 Xuhong Li, Yves GRANDVALET, Rémi Flamary, Nicolas Courty, Dejing Dou

We use optimal transport to quantify the match between two representations, yielding a distance that embeds some invariances inherent to the representation of deep networks.

Knowledge Distillation Model Compression +1

RIFLE: Backpropagation in Depth for Deep Transfer Learning through Re-Initializing the Fully-connected LayEr

1 code implementation ICML 2020 Xingjian Li, Haoyi Xiong, Haozhe An, Cheng-Zhong Xu, Dejing Dou

RIFLE brings meaningful updates to the weights of deep CNN layers and improves low-level feature learning, while the effects of randomization can be easily converged throughout the overall learning procedure.

Transfer Learning

Exploiting the Syntax-Model Consistency for Neural Relation Extraction

no code implementations ACL 2020 Amir Pouran Ben Veyseh, Franck Dernoncourt, Dejing Dou, Thien Huu Nguyen

In order to overcome these issues, we propose a novel deep learning model for RE that uses the dependency trees to extract the syntax-based importance scores for the words, serving as a tree representation to introduce syntactic information into the models with greater generalization.

Multi-Task Learning Relation +1

Cross-Task Transfer for Geotagged Audiovisual Aerial Scene Recognition

1 code implementation ECCV 2020 Di Hu, Xuhong LI, Lichao Mou, Pu Jin, Dong Chen, Liping Jing, Xiaoxiang Zhu, Dejing Dou

With the help of this dataset, we evaluate three proposed approaches for transferring the sound event knowledge to the aerial scene recognition task in a multimodal learning framework, and show the benefit of exploiting the audio information for the aerial scene recognition.

Scene Recognition

Ambient Sound Helps: Audiovisual Crowd Counting in Extreme Conditions

1 code implementation14 May 2020 Di Hu, Lichao Mou, Qingzhong Wang, Junyu. Gao, Yuansheng Hua, Dejing Dou, Xiao Xiang Zhu

Visual crowd counting has been recently studied as a way to enable people counting in crowd scenes from images.

Crowd Counting

Quantifying the Economic Impact of COVID-19 in Mainland China Using Human Mobility Data

no code implementations6 May 2020 Jizhou Huang, Haifeng Wang, Haoyi Xiong, Miao Fan, An Zhuo, Ying Li, Dejing Dou

While these strategies have effectively dealt with the critical situations of outbreaks, the combination of the pandemic and mobility controls has slowed China's economic growth, resulting in the first quarterly decline of Gross Domestic Product (GDP) since GDP began to be calculated, in 1992.

Pay Attention to Features, Transfer Learn Faster CNNs

no code implementations ICLR 2020 Kafeng Wang, Xitong Gao, Yiren Zhao, Xingjian Li, Dejing Dou, Cheng-Zhong Xu

Deep convolutional neural networks are now widely deployed in vision applications, but a limited size of training data can restrict their task performance.

Transfer Learning

COLAM: Co-Learning of Deep Neural Networks and Soft Labels via Alternating Minimization

no code implementations26 Apr 2020 Xingjian Li, Haoyi Xiong, Haozhe An, Dejing Dou, Chengzhong Xu

Softening labels of training datasets with respect to data representations has been frequently used to improve the training of deep neural networks (DNNs).

General Classification

Ontology-based Interpretable Machine Learning for Textual Data

2 code implementations1 Apr 2020 Phung Lai, NhatHai Phan, Han Hu, Anuja Badeti, David Newman, Dejing Dou

In this paper, we introduce a novel interpreting framework that learns an interpretable model based on an ontology-based sampling technique to explain agnostic prediction models.

BIG-bench Machine Learning Interpretable Machine Learning

Parameter-Free Style Projection for Arbitrary Style Transfer

1 code implementation17 Mar 2020 Siyu Huang, Haoyi Xiong, Tianyang Wang, Bihan Wen, Qingzhong Wang, Zeyu Chen, Jun Huan, Dejing Dou

This paper further presents a real-time feed-forward model to leverage Style Projection for arbitrary image style transfer, which includes a regularization term for matching the semantics between input contents and stylized outputs.

Style Transfer

Label-guided Learning for Text Classification

no code implementations25 Feb 2020 Xien Liu, Song Wang, Xiao Zhang, Xinxin You, Ji Wu, Dejing Dou

In this study, we propose a label-guided learning framework LguidedLearn for text representation and classification.

General Classification Representation Learning +2

Curriculum Audiovisual Learning

no code implementations26 Jan 2020 Di Hu, Zheng Wang, Haoyi Xiong, Dong Wang, Feiping Nie, Dejing Dou

Associating sound and its producer in complex audiovisual scene is a challenging task, especially when we are lack of annotated training data.

Clustering

An Empirical Study on the Relation between Network Interpretability and Adversarial Robustness

1 code implementation7 Dec 2019 Adam Noack, Isaac Ahern, Dejing Dou, Boyang Li

We demonstrate that training the networks to have interpretable gradients improves their robustness to adversarial perturbations.

Adversarial Robustness Image Classification +2

A Joint Model for Definition Extraction with Syntactic Connection and Semantic Consistency

1 code implementation5 Nov 2019 Amir Pouran Ben Veyseh, Franck Dernoncourt, Dejing Dou, Thien Huu Nguyen

In this work, we propose a novel model for DE that simultaneously performs the two tasks in a single framework to benefit from their inter-dependencies.

Definition Extraction Multi-Task Learning +2

Language-independent Cross-lingual Contextual Representations

no code implementations25 Sep 2019 Xiao Zhang, Song Wang, Dejing Dou, Xien Liu, Thien Huu Nguyen, Ji Wu

Contextual representation models like BERT have achieved state-of-the-art performance on a diverse range of NLP tasks.

Transfer Learning Zero-Shot Cross-Lingual Transfer

Differential Privacy in Adversarial Learning with Provable Robustness

no code implementations25 Sep 2019 NhatHai Phan, My T. Thai, Ruoming Jin, Han Hu, Dejing Dou

In this paper, we aim to develop a novel mechanism to preserve differential privacy (DP) in adversarial learning for deep neural networks, with provable robustness to adversarial examples.

NormLime: A New Feature Importance Metric for Explaining Deep Neural Networks

no code implementations ICLR 2020 Isaac Ahern, Adam Noack, Luis Guzman-Nateras, Dejing Dou, Boyang Li, Jun Huan

The problem of explaining deep learning models, and model predictions generally, has attracted intensive interest recently.

Feature Importance

Improving Adversarial Robustness via Attention and Adversarial Logit Pairing

no code implementations23 Aug 2019 Dou Goodman, Xingjian Li, Ji Liu, Dejing Dou, Tao Wei

Finally, we conduct extensive experiments using a wide range of datasets and the experiment results show that our AT+ALP achieves the state of the art defense performance.

Adversarial Robustness

Learning Conceptual-Contextual Embeddings for Medical Text

no code implementations16 Aug 2019 Xiao Zhang, Dejing Dou, Ji Wu

External knowledge is often useful for natural language understanding tasks.

Natural Language Understanding

Improving Cross-Domain Performance for Relation Extraction via Dependency Prediction and Information Flow Control

no code implementations7 Jul 2019 Amir Pouran Ben Veyseh, Thien Huu Nguyen, Dejing Dou

The current deep learning models for relation extraction has mainly exploited this dependency information by guiding their computation along the structures of the dependency trees.

Domain Generalization Relation +1

Graph based Neural Networks for Event Factuality Prediction using Syntactic and Semantic Structures

1 code implementation ACL 2019 Amir Pouran Ben Veyseh, Thien Huu Nguyen, Dejing Dou

In this work, we introduce a novel graph-based neural network for EFP that can integrate the semantic and syntactic information more effectively.

Sentence

Heterogeneous Gaussian Mechanism: Preserving Differential Privacy in Deep Learning with Provable Robustness

4 code implementations2 Jun 2019 NhatHai Phan, Minh Vu, Yang Liu, Ruoming Jin, Dejing Dou, Xintao Wu, My T. Thai

In this paper, we propose a novel Heterogeneous Gaussian Mechanism (HGM) to preserve differential privacy in deep neural networks, with provable robustness against adversarial examples.

Preserving Differential Privacy in Adversarial Learning with Provable Robustness

no code implementations23 Mar 2019 NhatHai Phan, My T. Thai, Ruoming Jin, Han Hu, Dejing Dou

In this paper, we aim to develop a novel mechanism to preserve differential privacy (DP) in adversarial learning for deep neural networks, with provable robustness to adversarial examples.

Cryptography and Security

Logic Rules Powered Knowledge Graph Embedding

no code implementations9 Mar 2019 Pengwei Wang, Dejing Dou, Fangzhao Wu, Nisansa de Silva, Lianwen Jin

And then, to put both triples and mined logic rules within the same semantic space, all triples in the knowledge graph are represented as first-order logic.

Knowledge Graph Embedding Link Prediction +1

Delta Embedding Learning

no code implementations ACL 2019 Xiao Zhang, Ji Wu, Dejing Dou

Evaluation also confirms the tuned word embeddings have better semantic properties.

Reading Comprehension Word Embeddings

On Adversarial Examples for Character-Level Neural Machine Translation

3 code implementations COLING 2018 Javid Ebrahimi, Daniel Lowd, Dejing Dou

Evaluating on adversarial examples has become a standard procedure to measure robustness of deep learning models.

Machine Translation NMT +1

HotFlip: White-Box Adversarial Examples for Text Classification

2 code implementations ACL 2018 Javid Ebrahimi, Anyi Rao, Daniel Lowd, Dejing Dou

We propose an efficient method to generate white-box adversarial examples to trick a character-level neural classifier.

General Classification text-classification +1

Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning

2 code implementations18 Sep 2017 NhatHai Phan, Xintao Wu, Han Hu, Dejing Dou

In this paper, we focus on developing a novel mechanism to preserve differential privacy in deep neural networks, such that: (1) The privacy budget consumption is totally independent of the number of training steps; (2) It has the ability to adaptively inject noise into features based on the contribution of each to the output; and (3) It could be applied in a variety of different deep neural networks.

Preserving Differential Privacy in Convolutional Deep Belief Networks

2 code implementations25 Jun 2017 NhatHai Phan, Xintao Wu, Dejing Dou

However, only a few scientific studies on preserving privacy in deep learning have been conducted.

A Probabilistic Approach to Knowledge Translation

no code implementations12 Jul 2015 Shangpu Jiang, Daniel Lowd, Dejing Dou

In this paper, we focus on a novel knowledge reuse scenario where the knowledge in the source schema needs to be translated to a semantically heterogeneous target schema.

Transfer Learning Translation

Ontology Matching with Knowledge Rules

no code implementations11 Jul 2015 Shangpu Jiang, Daniel Lowd, Dejing Dou

We use a probabilistic framework to integrate this new knowledge-based strategy with standard terminology-based and structure-based strategies.

Ontology Matching

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