Search Results for author: Di Wang

Found 146 papers, 49 papers with code

p-Norm Flow Diffusion for Local Graph Clustering

1 code implementation ICML 2020 Kimon Fountoulakis, Di Wang, Shenghao Yang

Local graph clustering and the closely related seed set expansion problem are primitives on graphs that are central to a wide range of analytic and learning tasks such as local clustering, community detection, nodes ranking and feature inference.

Clustering Community Detection +1

MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining

1 code implementation20 Mar 2024 Di Wang, Jing Zhang, Minqiang Xu, Lin Liu, Dongsheng Wang, Erzhong Gao, Chengxi Han, HaoNan Guo, Bo Du, DaCheng Tao, Liangpei Zhang

However, transferring the pretrained models to downstream tasks may encounter task discrepancy due to their formulation of pretraining as image classification or object discrimination tasks.

 Ranked #1 on Semantic Segmentation on SpaceNet 1 (using extra training data)

Aerial Scene Classification Building change detection for remote sensing images +13

Has Approximate Machine Unlearning been evaluated properly? From Auditing to Side Effects

no code implementations19 Mar 2024 Cheng-Long Wang, Qi Li, Zihang Xiang, Di Wang

The growing concerns surrounding data privacy and security have underscored the critical necessity for machine unlearning--aimed at fully removing data lineage from machine learning models.

Machine Unlearning

How Does Selection Leak Privacy: Revisiting Private Selection and Improved Results for Hyper-parameter Tuning

no code implementations20 Feb 2024 Zihang Xiang, Chenglong Wang, Di Wang

Recent works propose a generic private solution for the tuning process, yet a fundamental question still persists: is the current privacy bound for this solution tight?

Privacy-Preserving Low-Rank Adaptation for Latent Diffusion Models

1 code implementation19 Feb 2024 Zihao Luo, Xilie Xu, Feng Liu, Yun Sing Koh, Di Wang, Jingfeng Zhang

To mitigate this issue, we propose Stable PrivateLoRA that adapts the LDM by minimizing the ratio of the adaptation loss to the MI gain, which implicitly rescales the gradient and thus stabilizes the optimization.

Privacy Preserving

Human-AI Interactions in the Communication Era: Autophagy Makes Large Models Achieving Local Optima

no code implementations17 Feb 2024 Shu Yang, Lijie Hu, Lu Yu, Muhammad Asif Ali, Di Wang

The increasing significance of large language and multimodal models in societal information processing has ignited debates on social safety and ethics.

Ethics

MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning

no code implementations17 Feb 2024 Shu Yang, Muhammad Asif Ali, Cheng-Long Wang, Lijie Hu, Di Wang

Adapting large language models (LLMs) to new domains/tasks and enabling them to be efficient lifelong learners is a pivotal challenge.

NIV-SSD: Neighbor IoU-Voting Single-Stage Object Detector From Point Cloud

1 code implementation23 Jan 2024 Shuai Liu, Di Wang, Quan Wang, Kai Huang

NIV strategy can serve as a bridge between classification and regression branches by calculating two types of statistical data from the regression output to correct the classification confidence.

Classification Data Augmentation +1

Communication Efficient and Provable Federated Unlearning

no code implementations19 Jan 2024 Youming Tao, Cheng-Long Wang, Miao Pan, Dongxiao Yu, Xiuzhen Cheng, Di Wang

We start by giving a rigorous definition of \textit{exact} federated unlearning, which guarantees that the unlearned model is statistically indistinguishable from the one trained without the deleted data.

Federated Learning

Antonym vs Synonym Distinction using InterlaCed Encoder NETworks (ICE-NET)

no code implementations18 Jan 2024 Muhammad Asif Ali, Yan Hu, Jianbin Qin, Di Wang

In this paper, we propose InterlaCed Encoder NETworks (i. e., ICE-NET) for antonym vs synonym distinction, that aim to capture and model the relation-specific properties of the antonyms and synonyms pairs in order to perform the classification task in a performance-enhanced manner.

Relation

Weighted Spectral Filters for Kernel Interpolation on Spheres: Estimates of Prediction Accuracy for Noisy Data

no code implementations16 Jan 2024 Xiaotong Liu, Jinxin Wang, Di Wang, Shao-Bo Lin

In this paper, we introduce a weighted spectral filter approach to reduce the condition number of the kernel matrix and then stabilize kernel interpolation.

Image Reconstruction

A comprehensive framework for occluded human pose estimation

no code implementations30 Dec 2023 Linhao Xu, Lin Zhao, Xinxin Sun, Di Wang, Guangyu Li, Kedong Yan

The challenges posed by occlusion can be attributed to the following factors: 1) Data: The collection and annotation of occluded human pose samples are relatively challenging.

Data Augmentation Pose Estimation

Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning

1 code implementation29 Dec 2023 Zhongzhi Chen, Xingwu Sun, Xianfeng Jiao, Fengzong Lian, Zhanhui Kang, Di Wang, Cheng-Zhong Xu

We introduce Truth Forest, a method that enhances truthfulness in LLMs by uncovering hidden truth representations using multi-dimensional orthogonal probes.

Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks

no code implementations27 Dec 2023 Chenyang Qiu, Guoshun Nan, Tianyu Xiong, Wendi Deng, Di Wang, Zhiyang Teng, Lijuan Sun, Qimei Cui, Xiaofeng Tao

This finding motivates us to present a novel method that aims to harden GCNs by automatically learning Latent Homophilic Structures over heterophilic graphs.

Contrastive Learning Node Classification

Anchoring Path for Inductive Relation Prediction in Knowledge Graphs

1 code implementation21 Dec 2023 Zhixiang Su, Di Wang, Chunyan Miao, Lizhen Cui

To address this challenge, we propose Anchoring Path Sentence Transformer (APST) by introducing Anchoring Paths (APs) to alleviate the reliance of CPs.

Inductive Relation Prediction Knowledge Graphs +4

SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation

1 code implementation17 Dec 2023 Xiaoqi An, Lin Zhao, Chen Gong, Nannan Wang, Di Wang, Jian Yang

In this paper, we address the following question: "Only sparse human keypoint locations are detected for human pose estimation, is it really necessary to describe the whole image in a dense, high-resolution manner?"

Pose Estimation

Improving Faithfulness for Vision Transformers

no code implementations29 Nov 2023 Lijie Hu, Yixin Liu, Ninghao Liu, Mengdi Huai, Lichao Sun, Di Wang

However, ViTs suffer from issues with explanation faithfulness, as their focal points are fragile to adversarial attacks and can be easily changed with even slight perturbations on the input image.

Denoising

Fair Text-to-Image Diffusion via Fair Mapping

no code implementations29 Nov 2023 Jia Li, Lijie Hu, Jingfeng Zhang, Tianhang Zheng, Hua Zhang, Di Wang

In this paper, we address the limitations of existing text-to-image diffusion models in generating demographically fair results when given human-related descriptions.

Fairness Text-to-Image Generation

Preserving Node-level Privacy in Graph Neural Networks

no code implementations12 Nov 2023 Zihang Xiang, Tianhao Wang, Di Wang

In this study, we propose a solution that specifically addresses the issue of node-level privacy.

Distributed Uncertainty Quantification of Kernel Interpolation on Spheres

no code implementations25 Oct 2023 Shao-Bo Lin, Xingping Sun, Di Wang

For radial basis function (RBF) kernel interpolation of scattered data, Schaback in 1995 proved that the attainable approximation error and the condition number of the underlying interpolation matrix cannot be made small simultaneously.

Uncertainty Quantification

GARI: Graph Attention for Relative Isomorphism of Arabic Word Embeddings

1 code implementation19 Oct 2023 Muhammad Asif Ali, Maha Alshmrani, Jianbin Qin, Yan Hu, Di Wang

Bilingual Lexical Induction (BLI) is a core challenge in NLP, it relies on the relative isomorphism of individual embedding spaces.

Graph Attention Word Embeddings

GRI: Graph-based Relative Isomorphism of Word Embedding Spaces

1 code implementation18 Oct 2023 Muhammad Asif Ali, Yan Hu, Jianbin Qin, Di Wang

Automated construction of bilingual dictionaries using monolingual embedding spaces is a core challenge in machine translation.

Machine Translation

Worst-Case Analysis is Maximum-A-Posteriori Estimation

no code implementations15 Oct 2023 Hongjun Wu, Di Wang

The worst-case resource usage of a program can provide useful information for many software-engineering tasks, such as performance optimization and algorithmic-complexity-vulnerability discovery.

Probabilistic Programming

Differentially Private Non-convex Learning for Multi-layer Neural Networks

no code implementations12 Oct 2023 Hanpu Shen, Cheng-Long Wang, Zihang Xiang, Yiming Ying, Di Wang

This paper focuses on the problem of Differentially Private Stochastic Optimization for (multi-layer) fully connected neural networks with a single output node.

Stochastic Optimization

Improved Analysis of Sparse Linear Regression in Local Differential Privacy Model

no code implementations11 Oct 2023 Liyang Zhu, Meng Ding, Vaneet Aggarwal, Jinhui Xu, Di Wang

To address these issues, we first consider the problem in the $\epsilon$ non-interactive LDP model and provide a lower bound of $\Omega(\frac{\sqrt{dk\log d}}{\sqrt{n}\epsilon})$ on the $\ell_2$-norm estimation error for sub-Gaussian data, where $n$ is the sample size and $d$ is the dimension of the space.

regression

Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach

1 code implementation9 Oct 2023 Shaopeng Fu, Di Wang

Adversarial training (AT) is a canonical method for enhancing the robustness of deep neural networks (DNNs).

Fake News Detectors are Biased against Texts Generated by Large Language Models

no code implementations15 Sep 2023 Jinyan Su, Terry Yue Zhuo, Jonibek Mansurov, Di Wang, Preslav Nakov

The spread of fake news has emerged as a critical challenge, undermining trust and posing threats to society.

Misinformation

Adaptive Distributed Kernel Ridge Regression: A Feasible Distributed Learning Scheme for Data Silos

no code implementations8 Sep 2023 Di Wang, Xiaotong Liu, Shao-Bo Lin, Ding-Xuan Zhou

Data silos, mainly caused by privacy and interoperability, significantly constrain collaborations among different organizations with similar data for the same purpose.

Decision Making regression

On the Global Convergence of Natural Actor-Critic with Two-layer Neural Network Parametrization

no code implementations18 Jun 2023 Mudit Gaur, Amrit Singh Bedi, Di Wang, Vaneet Aggarwal

To achieve that, we propose a Natural Actor-Critic algorithm with 2-Layer critic parametrization (NAC2L).

Decision Making

Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards

no code implementations1 Jun 2023 Yulian Wu, Xingyu Zhou, Sayak Ray Chowdhury, Di Wang

Under each framework, we consider both joint differential privacy (JDP) and local differential privacy (LDP) models.

Multi-Armed Bandits reinforcement-learning

Generalization Guarantees of Gradient Descent for Multi-Layer Neural Networks

no code implementations26 May 2023 Puyu Wang, Yunwen Lei, Di Wang, Yiming Ying, Ding-Xuan Zhou

This sheds light on sufficient or necessary conditions for under-parameterized and over-parameterized NNs trained by GD to attain the desired risk rate of $O(1/\sqrt{n})$.

DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text

1 code implementation23 May 2023 Jinyan Su, Terry Yue Zhuo, Di Wang, Preslav Nakov

One is called DetectLLM-LRR, which is fast and efficient, and the other is called DetectLLM-NPR, which is more accurate, but slower due to the need for perturbations.

Misinformation

An Interactively Reinforced Paradigm for Joint Infrared-Visible Image Fusion and Saliency Object Detection

1 code implementation17 May 2023 Di Wang, JinYuan Liu, Risheng Liu, Xin Fan

Their common characteristic of seeking complementary cues from different source images motivates us to explore the collaborative relationship between Fusion and Salient object detection tasks on infrared and visible images via an Interactively Reinforced multi-task paradigm for the first time, termed IRFS.

Infrared And Visible Image Fusion object-detection +2

SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model

2 code implementations NeurIPS 2023 Di Wang, Jing Zhang, Bo Du, Minqiang Xu, Lin Liu, DaCheng Tao, Liangpei Zhang

In this study, we leverage SAM and existing RS object detection datasets to develop an efficient pipeline for generating a large-scale RS segmentation dataset, dubbed SAMRS.

Instance Segmentation Object +4

Revolutionizing Agrifood Systems with Artificial Intelligence: A Survey

no code implementations3 May 2023 Tao Chen, Liang Lv, Di Wang, Jing Zhang, Yue Yang, Zeyang Zhao, Chen Wang, Xiaowei Guo, Hao Chen, Qingye Wang, Yufei Xu, Qiming Zhang, Bo Du, Liangpei Zhang, DaCheng Tao

With the world population rapidly increasing, transforming our agrifood systems to be more productive, efficient, safe, and sustainable is crucial to mitigate potential food shortages.

HKNAS: Classification of Hyperspectral Imagery Based on Hyper Kernel Neural Architecture Search

1 code implementation23 Apr 2023 Di Wang, Bo Du, Liangpei Zhang, DaCheng Tao

Recent neural architecture search (NAS) based approaches have made great progress in hyperspectral image (HSI) classification tasks.

Neural Architecture Search

DCN-T: Dual Context Network with Transformer for Hyperspectral Image Classification

2 code implementations19 Apr 2023 Di Wang, Jing Zhang, Bo Du, Liangpei Zhang, DaCheng Tao

Hyperspectral image (HSI) classification is challenging due to spatial variability caused by complex imaging conditions.

Hyperspectral Image Classification Image Generation

Practical Differentially Private and Byzantine-resilient Federated Learning

1 code implementation15 Apr 2023 Zihang Xiang, Tianhao Wang, WanYu Lin, Di Wang

In contrast, we leverage the random noise to construct an aggregation that effectively rejects many existing Byzantine attacks.

Federated Learning Privacy Preserving

Inductive Graph Unlearning

1 code implementation6 Apr 2023 Cheng-Long Wang, Mengdi Huai, Di Wang

To extend machine unlearning to graph data, \textit{GraphEraser} has been proposed.

Fairness Graph Learning +2

Differentially Private Stochastic Convex Optimization in (Non)-Euclidean Space Revisited

no code implementations31 Mar 2023 Jinyan Su, Changhong Zhao, Di Wang

In this paper, we revisit the problem of Differentially Private Stochastic Convex Optimization (DP-SCO) in Euclidean and general $\ell_p^d$ spaces.

DIME-Net: Neural Network-Based Dynamic Intrinsic Parameter Rectification for Cameras with Optical Image Stabilization System

no code implementations20 Mar 2023 Shu-Hao Yeh, Shuangyu Xie, Di Wang, Wei Yan, Dezhen Song

Here we propose a novel neural network-based approach that estimates $\mathrm{K}$ matrix in real-time so that pose estimation or scene reconstruction can be run at camera native resolution for the highest accuracy on mobile devices.

3D Reconstruction Pose Estimation

Sketching with Spherical Designs for Noisy Data Fitting on Spheres

no code implementations8 Mar 2023 Shao-Bo Lin, Di Wang, Ding-Xuan Zhou

These interesting findings show that the proposed sketching strategy is capable of fitting massive and noisy data on spheres.

Kernel-Based Distributed Q-Learning: A Scalable Reinforcement Learning Approach for Dynamic Treatment Regimes

no code implementations21 Feb 2023 Di Wang, Yao Wang, Shaojie Tang, Shao-Bo Lin

The novelties of our research are as follows: 1) From a methodological perspective, we present a novel and scalable approach for generating DTRs by combining distributed learning with Q-learning.

Learning Theory Medical Diagnosis +2

Personalized and privacy-preserving federated heterogeneous medical image analysis with PPPML-HMI

1 code implementation20 Feb 2023 Juexiao Zhou, Longxi Zhou, Di Wang, Xiaopeng Xu, Haoyang Li, Yuetan Chu, Wenkai Han, Xin Gao

However, there are few open-source frameworks for federated heterogeneous medical image analysis with personalization and privacy protection simultaneously without the demand to modify the existing model structures or to share any private data.

Privacy Preserving

Robust Budget Pacing with a Single Sample

no code implementations3 Feb 2023 Santiago Balseiro, Rachitesh Kumar, Vahab Mirrokni, Balasubramanian Sivan, Di Wang

Given the inherent non-stationarity in an advertiser's value and also competing advertisers' values over time, a commonly used approach is to learn a target expenditure plan that specifies a target spend as a function of time, and then run a controller that tracks this plan.

Quantum Heavy-tailed Bandits

no code implementations23 Jan 2023 Yulian Wu, Chaowen Guan, Vaneet Aggarwal, Di Wang

In this paper, we study multi-armed bandits (MAB) and stochastic linear bandits (SLB) with heavy-tailed rewards and quantum reward oracle.

Multi-Armed Bandits

Differentially Private Natural Language Models: Recent Advances and Future Directions

no code implementations22 Jan 2023 Lijie Hu, Ivan Habernal, Lei Shen, Di Wang

In this paper, we provide the first systematic review of recent advances in DP deep learning models in NLP.

USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval

1 code implementation17 Jan 2023 Yan Zhang, Zhong Ji, Di Wang, Yanwei Pang, Xuelong Li

(2) It limits the scale of negative sample pairs by employing the mini-batch based end-to-end training mechanism.

Contrastive Learning Retrieval +3

Loss-Controlling Calibration for Predictive Models

no code implementations11 Jan 2023 Di Wang, Junzhi Shi, PingPing Wang, Shuo Zhuang, Hongyue Li

By comparison, the predictors built by the proposed loss-controlling approach are not limited to set predictors, and the loss function can be any measurable function without the monotone assumption.

Weather Forecasting

Conformal Loss-Controlling Prediction

no code implementations6 Jan 2023 Di Wang, Ping Wang, Zhong Ji, Xiaojun Yang, Hongyue Li

Conformal prediction is a learning framework controlling prediction coverage of prediction sets, which can be built on any learning algorithm for point prediction.

Conformal Prediction Weather Forecasting

Multi-Aspect Explainable Inductive Relation Prediction by Sentence Transformer

1 code implementation4 Jan 2023 Zhixiang Su, Di Wang, Chunyan Miao, Lizhen Cui

Recent studies on knowledge graphs (KGs) show that path-based methods empowered by pre-trained language models perform well in the provision of inductive and explainable relation predictions.

Inductive Relation Prediction Knowledge Graphs +2

Broad Learning System with Takagi-Sugeno Fuzzy Subsystem for Tobacco Origin Identification based on Near Infrared Spectroscopy

no code implementations31 Dec 2022 Di Wang, Simon X. Yang

In this paper, a novel broad learning system with Takagi-Sugeno (TS) fuzzy subsystem is proposed for rapid identification of tobacco origin.

Incremental Learning

Quantizing Heavy-tailed Data in Statistical Estimation: (Near) Minimax Rates, Covariate Quantization, and Uniform Recovery

no code implementations30 Dec 2022 Junren Chen, Michael K. Ng, Di Wang

Our major standpoint is that (near) minimax rates of estimation error are achievable merely from the quantized data produced by the proposed scheme.

Matrix Completion Quantization

Intelligent Feature Extraction, Data Fusion and Detection of Concrete Bridge Cracks: Current Development and Challenges

no code implementations24 Dec 2022 Di Wang, Simon X. Yang

As a common appearance defect of concrete bridges, cracks are important indices for bridge structure health assessment.

SEAT: Stable and Explainable Attention

no code implementations23 Nov 2022 Lijie Hu, Yixin Liu, Ninghao Liu, Mengdi Huai, Lichao Sun, Di Wang

Results show that SEAT is more stable against different perturbations and randomness while also keeps the explainability of attention, which indicates it is a more faithful explanation.

Semantic-aware Texture-Structure Feature Collaboration for Underwater Image Enhancement

1 code implementation19 Nov 2022 Di Wang, Long Ma, Risheng Liu, Xin Fan

To address the above limitations, we develop an efficient and compact enhancement network in collaboration with a high-level semantic-aware pretrained model, aiming to exploit its hierarchical feature representation as an auxiliary for the low-level underwater image enhancement.

Image Enhancement object-detection +2

1st ICLR International Workshop on Privacy, Accountability, Interpretability, Robustness, Reasoning on Structured Data (PAIR^2Struct)

no code implementations7 Oct 2022 Hao Wang, WanYu Lin, Hao He, Di Wang, Chengzhi Mao, Muhan Zhang

Recent years have seen advances on principles and guidance relating to accountable and ethical use of artificial intelligence (AI) spring up around the globe.

On Stability and Generalization of Bilevel Optimization Problem

no code implementations3 Oct 2022 Meng Ding, Mingxi Lei, Yunwen Lei, Di Wang, Jinhui Xu

In this paper, we conduct a thorough analysis on the generalization of first-order (gradient-based) methods for the bilevel optimization problem.

Bilevel Optimization Meta-Learning

On PAC Learning Halfspaces in Non-interactive Local Privacy Model with Public Unlabeled Data

no code implementations17 Sep 2022 Jinyan Su, Jinhui Xu, Di Wang

In this paper, we study the problem of PAC learning halfspaces in the non-interactive local differential privacy model (NLDP).

PAC learning Self-Supervised Learning

Truthful Generalized Linear Models

no code implementations16 Sep 2022 Yuan Qiu, Jinyan Liu, Di Wang

In the first part of the paper, we consider the case where the covariates are sub-Gaussian and the responses are heavy-tailed where they only have the finite fourth moments.

regression

Online Bidding Algorithms for Return-on-Spend Constrained Advertisers

no code implementations29 Aug 2022 Zhe Feng, Swati Padmanabhan, Di Wang

We contribute a simple online algorithm that achieves near-optimal regret in expectation while always respecting the specified RoS constraint when the input sequence of queries are i. i. d.

KL-divergence Based Deep Learning for Discrete Time Model

no code implementations10 Aug 2022 Li Liu, Xiangeng Fang, Di Wang, Weijing Tang, Kevin He

Neural Network (Deep Learning) is a modern model in Artificial Intelligence and it has been exploited in Survival Analysis.

Survival Analysis Survival Prediction

Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model

2 code implementations8 Aug 2022 Di Wang, Qiming Zhang, Yufei Xu, Jing Zhang, Bo Du, DaCheng Tao, Liangpei Zhang

Large-scale vision foundation models have made significant progress in visual tasks on natural images, with vision transformers being the primary choice due to their good scalability and representation ability.

Aerial Scene Classification Few-Shot Learning +2

Deep neural network heatmaps capture Alzheimer's disease patterns reported in a large meta-analysis of neuroimaging studies

no code implementations22 Jul 2022 Di Wang, Nicolas Honnorat, Peter T. Fox, Kerstin Ritter, Simon B. Eickhoff, Sudha Seshadri, Mohamad Habes

Deep neural networks currently provide the most advanced and accurate machine learning models to distinguish between structural MRI scans of subjects with Alzheimer's disease and healthy controls.

Unsupervised Misaligned Infrared and Visible Image Fusion via Cross-Modality Image Generation and Registration

1 code implementation24 May 2022 Di Wang, JinYuan Liu, Xin Fan, Risheng Liu

Moreover, to better fuse the registered infrared images and visible images, we present a feature Interaction Fusion Module (IFM) to adaptively select more meaningful features for fusion in the Dual-path Interaction Fusion Network (DIFN).

Image Generation Infrared And Visible Image Fusion +1

An Empirical Study of Remote Sensing Pretraining

2 code implementations6 Apr 2022 Di Wang, Jing Zhang, Bo Du, Gui-Song Xia, DaCheng Tao

To this end, we train different networks from scratch with the help of the largest RS scene recognition dataset up to now -- MillionAID, to obtain a series of RS pretrained backbones, including both convolutional neural networks (CNN) and vision transformers such as Swin and ViTAE, which have shown promising performance on computer vision tasks.

Aerial Scene Classification Building change detection for remote sensing images +5

High Dimensional Statistical Estimation under Uniformly Dithered One-bit Quantization

no code implementations26 Feb 2022 Junren Chen, Cheng-Long Wang, Michael K. Ng, Di Wang

In heavy-tailed regime, while the rates of our estimators become essentially slower, these results are either the first ones in an 1-bit quantized and heavy-tailed setting, or already improve on existing comparable results from some respect.

Low-Rank Matrix Completion Quantization +1

Differentially Private $\ell_1$-norm Linear Regression with Heavy-tailed Data

no code implementations10 Jan 2022 Di Wang, Jinhui Xu

Firstly, we study the case where the $\ell_2$ norm of data has bounded second order moment.

regression

VDPC: Variational Density Peak Clustering Algorithm

no code implementations29 Dec 2021 Yizhang Wang, Di Wang, You Zhou, Xiaofeng Zhang, Chai Quek

Furthermore, we divide all data points into different levels according to their local density and propose a unified clustering framework by combining the advantages of both DPC and DBSCAN.

Clustering

A Survey of Large-Scale Deep Learning Serving System Optimization: Challenges and Opportunities

no code implementations28 Nov 2021 Fuxun Yu, Di Wang, Longfei Shangguan, Minjia Zhang, Xulong Tang, ChenChen Liu, Xiang Chen

With both scaling trends, new problems and challenges emerge in DL inference serving systems, which gradually trends towards Large-scale Deep learning Serving systems (LDS).

Fed2: Feature-Aligned Federated Learning

no code implementations28 Nov 2021 Fuxun Yu, Weishan Zhang, Zhuwei Qin, Zirui Xu, Di Wang, ChenChen Liu, Zhi Tian, Xiang Chen

Federated learning learns from scattered data by fusing collaborative models from local nodes.

Federated Learning

Carousel Memory: Rethinking the Design of Episodic Memory for Continual Learning

1 code implementation14 Oct 2021 Soobee Lee, Minindu Weerakoon, Jonghyun Choi, Minjia Zhang, Di Wang, Myeongjae Jeon

In particular, in mobile and IoT devices, real-time data can be stored not just in high-speed RAMs but in internal storage devices as well, which offer significantly larger capacity than the RAMs.

Continual Learning Management

Incorporating Surprisingly Popular Algorithm and Euclidean Distance-based Adaptive Topology into PSO

1 code implementation25 Aug 2021 Xuan Wu, Jizong Han, Di Wang, Pengyue Gao, Quanlong Cui, Liang Chen, Yanchun Liang, Han Huang, Heow Pueh Lee, Chunyan Miao, You Zhou, Chunguo Wu

While many Particle Swarm Optimization (PSO) algorithms only use fitness to assess the performance of particles, in this work, we adopt Surprisingly Popular Algorithm (SPA) as a complementary metric in addition to fitness.

Single Particle Analysis

PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction

1 code implementation ACL 2021 Shulin Liu, Tao Yang, Tianchi Yue, Feng Zhang, Di Wang

In this paper, we propose a Pre-trained masked Language model with Misspelled knowledgE (PLOME) for CSC, which jointly learns how to understand language and correct spelling errors.

Language Modelling Spelling Correction

Concept-Based Label Embedding via Dynamic Routing for Hierarchical Text Classification

1 code implementation ACL 2021 Xuepeng Wang, Li Zhao, Bing Liu, Tao Chen, Feng Zhang, Di Wang

In this paper, we propose a novel concept-based label embedding method that can explicitly represent the concept and model the sharing mechanism among classes for the hierarchical text classification.

text-classification Text Classification

Faster Rates of Private Stochastic Convex Optimization

no code implementations31 Jul 2021 Jinyan Su, Lijie Hu, Di Wang

Specifically, we first show that under some mild assumptions on the loss functions, there is an algorithm whose output could achieve an upper bound of $\tilde{O}((\frac{1}{\sqrt{n}}+\frac{\sqrt{d\log \frac{1}{\delta}}}{n\epsilon})^\frac{\theta}{\theta-1})$ for $(\epsilon, \delta)$-DP when $\theta\geq 2$, here $n$ is the sample size and $d$ is the dimension of the space.

High Dimensional Differentially Private Stochastic Optimization with Heavy-tailed Data

no code implementations23 Jul 2021 Lijie Hu, Shuo Ni, Hanshen Xiao, Di Wang

To better understand the challenges arising from irregular data distribution, in this paper we provide the first study on the problem of DP-SCO with heavy-tailed data in the high dimensional space.

Sparse Learning Stochastic Optimization +1

Spectral-Spatial Global Graph Reasoning for Hyperspectral Image Classification

2 code implementations26 Jun 2021 Di Wang, Bo Du, Liangpei Zhang

To tackle these problems, in this paper, different from previous approaches, we perform the superpixel generation on intermediate features during network training to adaptively produce homogeneous regions, obtain graph structures, and further generate spatial descriptors, which are served as graph nodes.

Classification Hyperspectral Image Classification

UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase Prediction

1 code implementation Findings (ACL) 2021 Huanqin Wu, Wei Liu, Lei LI, Dan Nie, Tao Chen, Feng Zhang, Di Wang

Keyphrase Prediction (KP) task aims at predicting several keyphrases that can summarize the main idea of the given document.

Relation

Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits

no code implementations4 Jun 2021 Youming Tao, Yulian Wu, Peng Zhao, Di Wang

Finally, we establish the lower bound to show that the instance-dependent regret of our improved algorithm is optimal.

Multi-Armed Bandits

$\ell_2$-norm Flow Diffusion in Near-Linear Time

no code implementations30 May 2021 Li Chen, Richard Peng, Di Wang

Diffusion is a fundamental graph procedure and has been a basic building block in a wide range of theoretical and empirical applications such as graph partitioning and semi-supervised learning on graphs.

Clustering Graph Clustering +3

GSA-Forecaster: Forecasting Graph-Based Time-Dependent Data with Graph Sequence Attention

no code implementations13 Apr 2021 Yang Li, Di Wang, José M. F. Moura

This task is challenging as models need not only to capture spatial dependency and temporal dependency within the data, but also to leverage useful auxiliary information for accurate predictions.

3DMNDT:3D multi-view registration method based on the normal distributions transform

no code implementations20 Mar 2021 Jihua Zhu, Di Wang, Jiaxi Mu, Huimin Lu, Zhiqiang Tian, Zhongyu Li

Under the NDT framework, this paper proposes a novel multi-view registration method, named 3D multi-view registration based on the normal distributions transform (3DMNDT), which integrates the K-means clustering and Lie algebra solver to achieve multi-view registration.

Clustering

Minimum Cost Flows, MDPs, and $\ell_1$-Regression in Nearly Linear Time for Dense Instances

no code implementations14 Jan 2021 Jan van den Brand, Yin Tat Lee, Yang P. Liu, Thatchaphol Saranurak, Aaron Sidford, Zhao Song, Di Wang

In the special case of the minimum cost flow problem on $n$-vertex $m$-edge graphs with integer polynomially-bounded costs and capacities we obtain a randomized method which solves the problem in $\tilde{O}(m+n^{1. 5})$ time.

Data Structures and Algorithms Optimization and Control

CARE: Commonsense-Aware Emotional Response Generation with Latent Concepts

no code implementations15 Dec 2020 Peixiang Zhong, Di Wang, Pengfei Li, Chen Zhang, Hao Wang, Chunyan Miao

Experimental results on two large-scale datasets support our hypothesis and show that our model can produce more accurate and commonsense-aware emotional responses and achieve better human ratings than state-of-the-art models that only specialize in one aspect.

Response Generation

Third ArchEdge Workshop: Exploring the Design Space of Efficient Deep Neural Networks

no code implementations22 Nov 2020 Fuxun Yu, Dimitrios Stamoulis, Di Wang, Dimitrios Lymberopoulos, Xiang Chen

This paper gives an overview of our ongoing work on the design space exploration of efficient deep neural networks (DNNs).

Empirical Risk Minimization in the Non-interactive Local Model of Differential Privacy

no code implementations11 Nov 2020 Di Wang, Marco Gaboardi, Adam Smith, Jinhui Xu

In our second attempt, we show that for any $1$-Lipschitz generalized linear convex loss function, there is an $(\epsilon, \delta)$-LDP algorithm whose sample complexity for achieving error $\alpha$ is only linear in the dimensionality $p$.

Deep Learning Analysis and Age Prediction from Shoeprints

1 code implementation7 Nov 2020 Muhammad Hassan, Yan Wang, Di Wang, Daixi Li, Yanchun Liang, You Zhou, Dong Xu

We collected 100, 000 shoeprints of subjects ranging from 7 to 80 years old and used the data to develop a deep learning end-to-end model ShoeNet to analyze age-related patterns and predict age.

Gender Classification

Differentially Private (Gradient) Expectation Maximization Algorithm with Statistical Guarantees

no code implementations22 Oct 2020 Di Wang, Jiahao Ding, Lijie Hu, Zejun Xie, Miao Pan, Jinhui Xu

To address this issue, we propose in this paper the first DP version of (Gradient) EM algorithm with statistical guarantees.

On Differentially Private Stochastic Convex Optimization with Heavy-tailed Data

no code implementations ICML 2020 Di Wang, Hanshen Xiao, Srini Devadas, Jinhui Xu

For this case, we propose a method based on the sample-and-aggregate framework, which has an excess population risk of $\tilde{O}(\frac{d^3}{n\epsilon^4})$ (after omitting other factors), where $n$ is the sample size and $d$ is the dimensionality of the data.

Estimating Stochastic Linear Combination of Non-linear Regressions Efficiently and Scalably

no code implementations19 Oct 2020 Di Wang, Xiangyu Guo, Chaowen Guan, Shi Li, Jinhui Xu

To the best of our knowledge, this is the first work that studies and provides theoretical guarantees for the stochastic linear combination of non-linear regressions model.

LEMMA

Robust High Dimensional Expectation Maximization Algorithm via Trimmed Hard Thresholding

no code implementations19 Oct 2020 Di Wang, Xiangyu Guo, Shi Li, Jinhui Xu

In this paper, we study the problem of estimating latent variable models with arbitrarily corrupted samples in high dimensional space ({\em i. e.,} $d\gg n$) where the underlying parameter is assumed to be sparse.

Vocal Bursts Intensity Prediction

Learning Robust Algorithms for Online Allocation Problems Using Adversarial Training

no code implementations16 Oct 2020 Goran Zuzic, Di Wang, Aranyak Mehta, D. Sivakumar

In this paper, we focus on the AdWords problem, which is a classical online budgeted matching problem of both theoretical and practical significance.

ECG Beats Fast Classification Base on Sparse Dictionaries

1 code implementation8 Sep 2020 Nanyu Li, Yujuan Si, Di Wang, Tong Liu, Jinrun Yu

In VQ method, a set of dictionaries corresponding to segments of ECG beats is trained, and VQ codes are used to represent each heartbeat.

Classification Dictionary Learning +3

Heterogeneous Federated Learning

no code implementations15 Aug 2020 Fuxun Yu, Weishan Zhang, Zhuwei Qin, Zirui Xu, Di Wang, ChenChen Liu, Zhi Tian, Xiang Chen

Specifically, we design a feature-oriented regulation method ({$\Psi$-Net}) to ensure explicit feature information allocation in different neural network structures.

Federated Learning

AntiDote: Attention-based Dynamic Optimization for Neural Network Runtime Efficiency

no code implementations14 Aug 2020 Fuxun Yu, ChenChen Liu, Di Wang, Yanzhi Wang, Xiang Chen

Based on the neural network attention mechanism, we propose a comprehensive dynamic optimization framework including (1) testing-phase channel and column feature map pruning, as well as (2) training-phase optimization by targeted dropout.

Raising Expectations: Automating Expected Cost Analysis with Types

no code implementations24 Jun 2020 Di Wang, David M Kahn, Jan Hoffmann

The effectiveness of the technique is evaluated by analyzing the sample complexity of discrete distributions and with a novel average-case estimation for deterministic programs that combines expected cost analysis with statistical methods.

Programming Languages

$p$-Norm Flow Diffusion for Local Graph Clustering

2 code implementations20 May 2020 Kimon Fountoulakis, Di Wang, Shenghao Yang

Local graph clustering and the closely related seed set expansion problem are primitives on graphs that are central to a wide range of analytic and learning tasks such as local clustering, community detection, nodes ranking and feature inference.

Clustering Community Detection +1

Towards Assessment of Randomized Smoothing Mechanisms for Certifying Adversarial Robustness

no code implementations15 May 2020 Tianhang Zheng, Di Wang, Baochun Li, Jinhui Xu

Based on our framework, we assess the Gaussian and Exponential mechanisms by comparing the magnitude of additive noise required by these mechanisms and the lower bounds (criteria).

Adversarial Robustness

Distributed Kernel Ridge Regression with Communications

no code implementations27 Mar 2020 Shao-Bo Lin, Di Wang, Ding-Xuan Zhou

This paper focuses on generalization performance analysis for distributed algorithms in the framework of learning theory.

Learning Theory regression

Robust Feature-Based Point Registration Using Directional Mixture Model

no code implementations25 Nov 2019 Saman Fahandezh-Saadi, Di Wang, Masayoshi Tomizuka

This paper presents a robust probabilistic point registration method for estimating the rigid transformation (i. e. rotation matrix and translation vector) between two pointcloud dataset.

Translation

Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning

1 code implementation17 Nov 2019 Fuxun Yu, Di Wang, Yinpeng Chen, Nikolaos Karianakis, Tong Shen, Pei Yu, Dimitrios Lymberopoulos, Sidi Lu, Weisong Shi, Xiang Chen

In this work, we show that such adversarial-based methods can only reduce the domain style gap, but cannot address the domain content distribution gap that is shown to be important for object detectors.

Object object-detection +2

Facility Location Problem in Differential Privacy Model Revisited

no code implementations NeurIPS 2019 Yunus Esencayi, Marco Gaboardi, Shi Li, Di Wang

On the negative side, we show that the approximation ratio of any $\epsilon$-DP algorithm is lower bounded by $\Omega(\frac{1}{\sqrt{\epsilon}})$, even for instances on HST metrics with uniform facility cost, under the super-set output setting.

Estimating Smooth GLM in Non-interactive Local Differential Privacy Model with Public Unlabeled Data

no code implementations1 Oct 2019 Di Wang, Lijie Hu, Huanyu Zhang, Marco Gaboardi, Jinhui Xu

In the second part of the paper, we extend our idea to the problem of estimating non-linear regressions and show similar results as in GLMs for both multivariate Gaussian and sub-Gaussian cases.

LEMMA

Faster width-dependent algorithm for mixed packing and covering LPs

no code implementations NeurIPS 2019 Digvijay Boob, Saurabh Sawlani, Di Wang

As a special case of our result, we report a $1+\eps$ approximation algorithm for the densest subgraph problem which runs in time $O(md/ \eps)$, where $m$ is the number of edges in the graph and $d$ is the maximum graph degree.

Combinatorial Optimization

A Unified framework for randomized smoothing based certified defenses

no code implementations25 Sep 2019 Tianhang Zheng, Di Wang, Baochun Li, Jinhui Xu

We answer the above two questions by first demonstrating that Gaussian mechanism and Exponential mechanism are the (near) optimal options to certify the $\ell_2$ and $\ell_\infty$-normed robustness.

YaoGAN: Learning Worst-case Competitive Algorithms from Self-generated Inputs

no code implementations25 Sep 2019 Goran Zuzic, Di Wang, Aranyak Mehta, D. Sivakumar

To answer this question, we draw insights from classic results in game theory, analysis of algorithms, and online learning to introduce a novel framework.

Combinatorial Optimization Generative Adversarial Network

Heterogeneous-Temporal Graph Convolutional Networks: Make the Community Detection Much Better

no code implementations23 Sep 2019 Yaping Zheng, Shiyi Chen, Xinni Zhang, Xiaofeng Zhang, Xiaofei Yang, Di Wang

Community detection has long been an important yet challenging task to analyze complex networks with a focus on detecting topological structures of graph data.

Community Detection

Distributed Equivalent Substitution Training for Large-Scale Recommender Systems

no code implementations10 Sep 2019 Haidong Rong, Yangzihao Wang, Feihu Zhou, Junjie Zhai, Haiyang Wu, Rui Lan, Fan Li, Han Zhang, Yuekui Yang, Zhenyu Guo, Di Wang

We present Distributed Equivalent Substitution (DES) training, a novel distributed training framework for large-scale recommender systems with dynamic sparse features.

Recommendation Systems

Compact Autoregressive Network

no code implementations6 Sep 2019 Di Wang, Feiqing Huang, Jingyu Zhao, Guodong Li, Guangjian Tian

Autoregressive networks can achieve promising performance in many sequence modeling tasks with short-range dependence.

TAR

EEG-Based Emotion Recognition Using Regularized Graph Neural Networks

2 code implementations18 Jul 2019 Peixiang Zhong, Di Wang, Chunyan Miao

Finally, investigations on the neuronal activities reveal important brain regions and inter-channel relations for EEG-based emotion recognition.

EEG EEG Emotion Recognition +1

Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization

1 code implementation1 Jul 2019 Dimitrios Stamoulis, Ruizhou Ding, Di Wang, Dimitrios Lymberopoulos, Bodhi Priyantha, Jie Liu, Diana Marculescu

In this work, we alleviate the NAS search cost down to less than 3 hours, while achieving state-of-the-art image classification results under mobile latency constraints.

Hyperparameter Optimization Image Classification +1

Neural Learning of Online Consumer Credit Risk

no code implementations5 Jun 2019 Di Wang, Qi Wu, Wen Zhang

This paper takes a deep learning approach to understand consumer credit risk when e-commerce platforms issue unsecured credit to finance customers' purchase.

Time Series Time Series Analysis

Single-Path NAS: Device-Aware Efficient ConvNet Design

no code implementations10 May 2019 Dimitrios Stamoulis, Ruizhou Ding, Di Wang, Dimitrios Lymberopoulos, Bodhi Priyantha, Jie Liu, Diana Marculescu

Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the latency constraint of a mobile device?

General Classification Image Classification +1

Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours

9 code implementations5 Apr 2019 Dimitrios Stamoulis, Ruizhou Ding, Di Wang, Dimitrios Lymberopoulos, Bodhi Priyantha, Jie Liu, Diana Marculescu

Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the runtime constraint of a mobile device?

General Classification Image Classification +1

Density Matching for Bilingual Word Embedding

1 code implementation NAACL 2019 Chunting Zhou, Xuezhe Ma, Di Wang, Graham Neubig

Recent approaches to cross-lingual word embedding have generally been based on linear transformations between the sets of embedding vectors in the two languages.

Bilingual Lexicon Induction Word Embeddings +1

Differentially Private High Dimensional Sparse Covariance Matrix Estimation

no code implementations18 Jan 2019 Di Wang, Jinhui Xu

In this paper, we study the problem of estimating the covariance matrix under differential privacy, where the underlying covariance matrix is assumed to be sparse and of high dimensions.

Vocal Bursts Intensity Prediction

Expander Decomposition and Pruning: Faster, Stronger, and Simpler

1 code implementation21 Dec 2018 Thatchaphol Saranurak, Di Wang

Our result achieve both nearly linear running time and the strong expander guarantee for clusters.

Data Structures and Algorithms

Noninteractive Locally Private Learning of Linear Models via Polynomial Approximations

no code implementations17 Dec 2018 Di Wang, Adam Smith, Jinhui Xu

For the case of \emph{generalized linear losses} (such as hinge and logistic losses), we give an LDP algorithm whose sample complexity is only linear in the dimensionality $p$ and quasipolynomial in other terms (the privacy parameters $\epsilon$ and $\delta$, and the desired excess risk $\alpha$).

Empirical Risk Minimization in Non-interactive Local Differential Privacy Revisited

no code implementations NeurIPS 2018 Di Wang, Marco Gaboardi, Jinhui Xu

In this paper, we revisit the Empirical Risk Minimization problem in the non-interactive local model of differential privacy.

Tackling Adversarial Examples in QA via Answer Sentence Selection

no code implementations WS 2018 Yuanhang Ren, Ye Du, Di Wang

Given a paragraph of an article and a corresponding query, instead of directly feeding the whole paragraph to the single BiDAF system, a sentence that most likely contains the answer to the query is first selected, which is done via a deep neural network based on TreeLSTM (Tai et al., 2015).

Question Answering Reading Comprehension +1

Neural Machine Translation with Key-Value Memory-Augmented Attention

no code implementations29 Jun 2018 Fandong Meng, Zhaopeng Tu, Yong Cheng, Haiyang Wu, Junjie Zhai, Yuekui Yang, Di Wang

Although attention-based Neural Machine Translation (NMT) has achieved remarkable progress in recent years, it still suffers from issues of repeating and dropping translations.

Machine Translation NMT +2

Differentially Private Empirical Risk Minimization Revisited: Faster and More General

no code implementations NeurIPS 2017 Di Wang, Minwei Ye, Jinhui Xu

In this paper we study the differentially private Empirical Risk Minimization (ERM) problem in different settings.

Empirical Risk Minimization in Non-interactive Local Differential Privacy: Efficiency and High Dimensional Case

no code implementations NeurIPS 2018 Di Wang, Marco Gaboardi, Jinhui Xu

In the case of constant or low dimensionality ($p\ll n$), we first show that if the ERM loss function is $(\infty, T)$-smooth, then we can avoid a dependence of the sample complexity, to achieve error $\alpha$, on the exponential of the dimensionality $p$ with base $1/\alpha$ (i. e., $\alpha^{-p}$), which answers a question in [smith 2017 interaction].

Large Scale Constrained Linear Regression Revisited: Faster Algorithms via Preconditioning

1 code implementation9 Feb 2018 Di Wang, Jinhui Xu

In this paper, we revisit the large-scale constrained linear regression problem and propose faster methods based on some recent developments in sketching and optimization.

regression

Steering Output Style and Topic in Neural Response Generation

1 code implementation EMNLP 2017 Di Wang, Nebojsa Jojic, Chris Brockett, Eric Nyberg

We propose simple and flexible training and decoding methods for influencing output style and topic in neural encoder-decoder based language generation.

Response Generation Text Generation

Capacity Releasing Diffusion for Speed and Locality

no code implementations19 Jun 2017 Di Wang, Kimon Fountoulakis, Monika Henzinger, Michael W. Mahoney, Satish Rao

Thus, our CRD Process is the first local graph clustering algorithm that is not subject to the well-known quadratic Cheeger barrier.

Clustering Graph Clustering

The Language Application Grid

no code implementations LREC 2014 Nancy Ide, James Pustejovsky, Christopher Cieri, Eric Nyberg, Di Wang, Keith Suderman, Marc Verhagen, Jonathan Wright

The Language Application (LAPPS) Grid project is establishing a framework that enables language service discovery, composition, and reuse and promotes sustainability, manageability, usability, and interoperability of natural language Processing (NLP) components.

Machine Translation Question Answering +1

Simultaneous Rectification and Alignment via Robust Recovery of Low-rank Tensors

no code implementations NeurIPS 2013 Xiaoqin Zhang, Di Wang, Zhengyuan Zhou, Yi Ma

In this context, the state-of-the-art algorithms RASL'' and "TILT'' can be viewed as two special cases of our work, and yet each only performs part of the function of our method."

Computational Efficiency

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