Search Results for author: Bo Li

Found 443 papers, 174 papers with code

Relative Pose Estimation of Calibrated Cameras with Known SE(3) Invariants

1 code implementation ECCV 2020 Bo Li, Evgeniy Martyushev, Gim Hee Lee

In this paper, we present a complete comprehensive study of the relative pose estimation problem for a calibrated camera constrained by known $\mathrm{SE}(3)$ invariant, which involves 5 minimal problems in total.

Pose Estimation Translation

Alibaba Speech Translation Systems for IWSLT 2018

no code implementations IWSLT (EMNLP) 2018 Nguyen Bach, Hongjie Chen, Kai Fan, Cheung-Chi Leung, Bo Li, Chongjia Ni, Rong Tong, Pei Zhang, Boxing Chen, Bin Ma, Fei Huang

This work describes the En→De Alibaba speech translation system developed for the evaluation campaign of the International Workshop on Spoken Language Translation (IWSLT) 2018.


Profanity-Avoiding Training Framework for Seq2seq Models with Certified Robustness

no code implementations EMNLP 2021 Hengtong Zhang, Tianhang Zheng, Yaliang Li, Jing Gao, Lu Su, Bo Li

To address this problem, we propose a training framework with certified robustness to eliminate the causes that trigger the generation of profanity.

Dialogue Generation Style Transfer

Invertible Convolution with Symmetric Paddings

1 code implementation30 Mar 2023 Bo Li

We show that symmetrically padded convolution can be analytically inverted via DFT.

Efficient Decision-based Black-box Patch Attacks on Video Recognition

no code implementations21 Mar 2023 Kaixun Jiang, Zhaoyu Chen, Tony Huang, Jiafeng Wang, Dingkang Yang, Bo Li, Yan Wang, Wenqiang Zhang

First, STDE introduces target videos as patch textures and only adds patches on keyframes that are adaptively selected by temporal difference.

Video Recognition

Graph Transformer GANs for Graph-Constrained House Generation

no code implementations14 Mar 2023 Hao Tang, Zhenyu Zhang, Humphrey Shi, Bo Li, Ling Shao, Nicu Sebe, Radu Timofte, Luc van Gool

We present a novel graph Transformer generative adversarial network (GTGAN) to learn effective graph node relations in an end-to-end fashion for the challenging graph-constrained house generation task.

House Generation Node Classification

TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets

1 code implementation10 Mar 2023 Weixin Chen, Dawn Song, Bo Li

To answer these questions, we propose an effective Trojan attack against diffusion models, TrojDiff, which optimizes the Trojan diffusion and generative processes during training.

Image Generation

Pose-Controllable 3D Facial Animation Synthesis using Hierarchical Audio-Vertex Attention

no code implementations24 Feb 2023 Bin Liu, Xiaolin Wei, Bo Li, Junjie Cao, Yu-Kun Lai

In this paper, a novel pose-controllable 3D facial animation synthesis method is proposed by utilizing hierarchical audio-vertex attention.

Face Model

Decoupling the All-Reduce Primitive for Accelerating Distributed Deep Learning

no code implementations24 Feb 2023 Lin Zhang, Shaohuai Shi, Xiaowen Chu, Wei Wang, Bo Li, Chengjian Liu

Communication scheduling has been shown to be effective in accelerating distributed training, which enables all-reduce communications to be overlapped with backpropagation computations.


UML: A Universal Monolingual Output Layer for Multilingual ASR

no code implementations22 Feb 2023 Chao Zhang, Bo Li, Tara N. Sainath, Trevor Strohman, Shuo-Yiin Chang

Consequently, the UML enables to switch in the interpretation of each output node depending on the language of the input speech.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Delving into the Adversarial Robustness of Federated Learning

no code implementations19 Feb 2023 Jie Zhang, Bo Li, Chen Chen, Lingjuan Lyu, Shuang Wu, Shouhong Ding, Chao Wu

In this work, we propose a novel algorithm called Decision Boundary based Federated Adversarial Training (DBFAT), which consists of two components (local re-weighting and global regularization) to improve both accuracy and robustness of FL systems.

Adversarial Robustness Federated Learning

JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition

no code implementations16 Feb 2023 Zhong Meng, Weiran Wang, Rohit Prabhavalkar, Tara N. Sainath, Tongzhou Chen, Ehsan Variani, Yu Zhang, Bo Li, Andrew Rosenberg, Bhuvana Ramabhadran

We propose JEIT, a joint end-to-end (E2E) model and internal language model (ILM) training method to inject large-scale unpaired text into ILM during E2E training which improves rare-word speech recognition.

Language Modelling speech-recognition +1

3D Colored Shape Reconstruction from a Single RGB Image through Diffusion

no code implementations11 Feb 2023 Bo Li, Xiaolin Wei, Fengwei Chen, Bin Liu

In shape prediction module, the reference RGB image is first encoded into a high-level shape feature and then the shape feature is utilized as a condition to predict the reverse geometric noise in diffusion model.

3D Reconstruction 3D Shape Generation +1

Interpolation for Robust Learning: Data Augmentation on Geodesics

no code implementations4 Feb 2023 Jiacheng Zhu, JieLin Qiu, Aritra Guha, Zhuolin Yang, XuanLong Nguyen, Bo Li, Ding Zhao

Our work provides a new perspective of model robustness through the lens of Wasserstein geodesic-based interpolation with a practical off-the-shelf strategy that can be combined with existing robust training methods.

Data Augmentation

Defensive ML: Defending Architectural Side-channels with Adversarial Obfuscation

no code implementations3 Feb 2023 Hyoungwook Nam, Raghavendra Pradyumna Pothukuchi, Bo Li, Nam Sung Kim, Josep Torrellas

To address this problem, this paper explores using Adversarial Machine Learning (AML) methods as a defense at the computer architecture layer to obfuscate side channels.

Computer Security

Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning

no code implementations26 Jan 2023 Mingqi Yuan, Bo Li, Xin Jin, Wenjun Zeng

We present AIRS: Automatic Intrinsic Reward Shaping that intelligently and adaptively provides high-quality intrinsic rewards to enhance exploration in reinforcement learning (RL).

Benchmarking reinforcement-learning +1

From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition

no code implementations19 Jan 2023 Chao-Han Huck Yang, Bo Li, Yu Zhang, Nanxin Chen, Rohit Prabhavalkar, Tara N. Sainath, Trevor Strohman

In this work, we propose a new parameter-efficient learning framework based on neural model reprogramming for cross-lingual speech recognition, which can \textbf{re-purpose} well-trained English automatic speech recognition (ASR) models to recognize the other languages.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Proportional Fairness in Obnoxious Facility Location

no code implementations11 Jan 2023 Haris Aziz, Alexander Lam, Bo Li, Fahimeh Ramezani, Toby Walsh

On the other hand, in the randomized setting, we identify proportionally fair and strategyproof mechanisms that give an expected welfare within a constant factor of the optimal welfare.


A Bertrand duopoly game with differentiated products reconsidered

no code implementations3 Jan 2023 Xiaoliang Li, Bo Li

In this paper, we explore a dynamic Bertrand duopoly game with differentiated products, where firms are boundedly rational and consumers are assumed to possess an underlying CES utility function.

Reviewing Labels: Label Graph Network with Top-k Prediction Set for Relation Extraction

no code implementations29 Dec 2022 Bo Li, Wei Ye, Jinglei Zhang, Shikun Zhang

Specifically, for a given sample, we build a label graph to review candidate labels in the Top-k prediction set and learn the connections between them.

Relation Extraction

Sequence Generation with Label Augmentation for Relation Extraction

1 code implementation29 Dec 2022 Bo Li, Dingyao Yu, Wei Ye, Jinglei Zhang, Shikun Zhang

Sequence generation demonstrates promising performance in recent information extraction efforts, by incorporating large-scale pre-trained Seq2Seq models.

Relation Extraction

EDoG: Adversarial Edge Detection For Graph Neural Networks

no code implementations27 Dec 2022 Xiaojun Xu, Yue Yu, Hanzhang Wang, Alok Lal, Carl A. Gunter, Bo Li

In this paper, we propose a general adversarial edge detection pipeline EDoG without requiring knowledge of the attack strategies based on graph generation.

Edge Detection Graph Generation +2

Forecasting West Nile Virus with Graph Neural Networks: Harnessing Spatial Dependence in Irregularly Sampled Geospatial Data

no code implementations21 Dec 2022 Adam Tonks, Trevor Harris, Bo Li, William Brown, Rebecca Smith

Machine learning methods have seen increased application to geospatial environmental problems, such as precipitation nowcasting, haze forecasting, and crop yield prediction.

Crop Yield Prediction regression

Partial Variance Reduction improves Non-Convex Federated learning on heterogeneous data

no code implementations5 Dec 2022 Bo Li, Mikkel N. Schmidt, Tommy S. Alstrøm, Sebastian U. Stich

In this paper, we first revisit the widely used FedAvg algorithm in a deep neural network to understand how data heterogeneity influences the gradient updates across the neural network layers.

Federated Learning

Logic and Commonsense-Guided Temporal Knowledge Graph Completion

1 code implementation30 Nov 2022 Guanglin Niu, Bo Li

To address these challenges, we propose a Logic and Commonsense-Guided Embedding model (LCGE) to jointly learn the time-sensitive representation involving timeliness and causality of events, together with the time-independent representation of events from the perspective of commonsense.

Causal Inference Knowledge Graph Completion +1

Rethinking Disparity: A Depth Range Free Multi-View Stereo Based on Disparity

1 code implementation30 Nov 2022 Qingsong Yan, Qiang Wang, Kaiyong Zhao, Bo Li, Xiaowen Chu, Fei Deng

Existing learning-based multi-view stereo (MVS) methods rely on the depth range to build the 3D cost volume and may fail when the range is too large or unreliable.

Confounder Balancing for Instrumental Variable Regression with Latent Variable

no code implementations18 Nov 2022 Anpeng Wu, Kun Kuang, Ruoxuan Xiong, Bo Li, Fei Wu

This paper studies the confounding effects from the unmeasured confounders and the imbalance of observed confounders in IV regression and aims at unbiased causal effect estimation.


AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies

1 code implementation10 Nov 2022 Li SiYao, Yuhang Li, Bo Li, Chao Dong, Ziwei Liu, Chen Change Loy

Existing correspondence datasets for two-dimensional (2D) cartoon suffer from simple frame composition and monotonic movements, making them insufficient to simulate real animations.

Optical Flow Estimation

HFedMS: Heterogeneous Federated Learning with Memorable Data Semantics in Industrial Metaverse

1 code implementation7 Nov 2022 Shenglai Zeng, Zonghang Li, Hongfang Yu, Zhihao Zhang, Long Luo, Bo Li, Dusit Niyato

Federated Learning (FL), as a rapidly evolving privacy-preserving collaborative machine learning paradigm, is a promising approach to enable edge intelligence in the emerging Industrial Metaverse.

Federated Learning Privacy Preserving

Resource-Efficient Transfer Learning From Speech Foundation Model Using Hierarchical Feature Fusion

no code implementations4 Nov 2022 Zhouyuan Huo, Khe Chai Sim, Bo Li, Dongseong Hwang, Tara N. Sainath, Trevor Strohman

Experimental results show that the proposed method can achieve better performance on speech recognition task than existing algorithms with fewer number of trainable parameters, less computational memory cost and faster training speed.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Fairness in Federated Learning via Core-Stability

no code implementations3 Nov 2022 Bhaskar Ray Chaudhury, Linyi Li, Mintong Kang, Bo Li, Ruta Mehta

Nonetheless, the heterogeneity nature of distributed data makes it challenging to define and ensure fairness among local agents.

Decision Making Fairness +1

A Quantum Kernel Learning Approach to Acoustic Modeling for Spoken Command Recognition

no code implementations2 Nov 2022 Chao-Han Huck Yang, Bo Li, Yu Zhang, Nanxin Chen, Tara N. Sainath, Sabato Marco Siniscalchi, Chin-Hui Lee

We propose a quantum kernel learning (QKL) framework to address the inherent data sparsity issues often encountered in training large-scare acoustic models in low-resource scenarios.

Spoken Command Recognition

DensePure: Understanding Diffusion Models towards Adversarial Robustness

no code implementations1 Nov 2022 Chaowei Xiao, Zhongzhu Chen, Kun Jin, Jiongxiao Wang, Weili Nie, Mingyan Liu, Anima Anandkumar, Bo Li, Dawn Song

By using the highest density point in the conditional distribution as the reversed sample, we identify the robust region of a given instance under the diffusion model's reverse process.

Adversarial Robustness Denoising

Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems

no code implementations1 Nov 2022 Shaan Bijwadia, Shuo-Yiin Chang, Bo Li, Tara Sainath, Chao Zhang, Yanzhang He

In this work, we propose a method to jointly train the ASR and EP tasks in a single end-to-end (E2E) multitask model, improving EP quality by optionally leveraging information from the ASR audio encoder.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Shape Matters: Deformable Patch Attack

1 code implementation European Conference on Computer Vision 2022 Zhaoyu Chen, Bo Li, Shuang Wu, Jianghe Xu, Shouhong Ding, Wenqiang Zhang

Though deep neural networks (DNNs) have demonstrated excellent performance in computer vision, they are susceptible and vulnerable to carefully crafted adversarial examples which can mislead DNNs to incorrect outputs.

CU-Net: LiDAR Depth-Only Completion With Coupled U-Net

1 code implementation26 Oct 2022 YuFei Wang, Yuchao Dai, Qi Liu, Peng Yang, Jiadai Sun, Bo Li

We find that existing depth-only methods can obtain satisfactory results in the areas where the measurement points are almost accurate and evenly distributed (denoted as normal areas), while the performance is limited in the areas where the foreground and background points are overlapped due to occlusion (denoted as overlap areas) and the areas where there are no measurement points around (denoted as blank areas) since the methods have no reliable input information in these areas.

LOT: Layer-wise Orthogonal Training on Improving $\ell_2$ Certified Robustness

1 code implementation20 Oct 2022 Xiaojun Xu, Linyi Li, Bo Li

On the other hand, as existing works show that semi-supervised training helps improve empirical robustness, we aim to bridge the gap and prove that semi-supervised learning also improves the certified robustness of Lipschitz-bounded models.

Adversarial Robustness

Joint Plasticity Learning for Camera Incremental Person Re-Identification

no code implementations17 Oct 2022 Zexian Yang, Dayan Wu, Bo Li, Weiping Wang

This is challenging as the new data only have local supervision in new cameras with no access to the old data due to privacy issues, and they may also contain persons seen by previous cameras.

Incremental Learning Person Re-Identification

Product Ranking for Revenue Maximization with Multiple Purchases

1 code implementation15 Oct 2022 Renzhe Xu, Xingxuan Zhang, Bo Li, Yafeng Zhang, Xiaolong Chen, Peng Cui

In this paper, we assume that each consumer can purchase multiple products at will.

OpenOOD: Benchmarking Generalized Out-of-Distribution Detection

1 code implementation13 Oct 2022 Jingkang Yang, Pengyun Wang, Dejian Zou, Zitang Zhou, Kunyuan Ding, Wenxuan Peng, Haoqi Wang, Guangyao Chen, Bo Li, Yiyou Sun, Xuefeng Du, Kaiyang Zhou, Wayne Zhang, Dan Hendrycks, Yixuan Li, Ziwei Liu

Out-of-distribution (OOD) detection is vital to safety-critical machine learning applications and has thus been extensively studied, with a plethora of methods developed in the literature.

Anomaly Detection Benchmarking +3

JOIST: A Joint Speech and Text Streaming Model For ASR

no code implementations13 Oct 2022 Tara N. Sainath, Rohit Prabhavalkar, Ankur Bapna, Yu Zhang, Zhouyuan Huo, Zhehuai Chen, Bo Li, Weiran Wang, Trevor Strohman

In addition, we explore JOIST using a streaming E2E model with an order of magnitude more data, which are also novelties compared to previous works.

Feature Reconstruction Attacks and Countermeasures of DNN training in Vertical Federated Learning

no code implementations13 Oct 2022 Peng Ye, Zhifeng Jiang, Wei Wang, Bo Li, Baochun Li

To address this problem, we develop a novel feature protection scheme against the reconstruction attack that effectively misleads the search to some pre-specified random values.

Federated Learning

Improving Long-tailed Object Detection with Image-Level Supervision by Multi-Task Collaborative Learning

1 code implementation11 Oct 2022 Bo Li, Yongqiang Yao, Jingru Tan, Xin Lu, Fengwei Yu, Ye Luo, Jianwei Lu

Specifically, there are an object detection task (consisting of an instance-classification task and a localization task) and an image-classification task in our framework, responsible for utilizing the two types of supervision.

Classification Contrastive Learning +3

Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment

no code implementations10 Oct 2022 JieLin Qiu, Jiacheng Zhu, Mengdi Xu, Franck Dernoncourt, Trung Bui, Zhaowen Wang, Bo Li, Ding Zhao, Hailin Jin

Multimedia summarization with multimodal output (MSMO) is a recently explored application in language grounding.

Towards Stable Co-saliency Detection and Object Co-segmentation

no code implementations25 Sep 2022 Bo Li, Lv Tang, Senyun Kuang, Mofei Song, Shouhong Ding

In this paper, we present a novel model for simultaneous stable co-saliency detection (CoSOD) and object co-segmentation (CoSEG).

Saliency Detection

Attributed Network Embedding Model for Exposing COVID-19 Spread Trajectory Archetypes

no code implementations20 Sep 2022 Junwei Ma, Bo Li, Qingchun Li, Chao Fan, Ali Mostafavi

To this end, this study creates a network embedding model capturing cross-county visitation networks, as well as heterogeneous features to uncover clusters of counties in the United States based on their pandemic spread transmission trajectories.

Network Embedding

Rewarding Episodic Visitation Discrepancy for Exploration in Reinforcement Learning

no code implementations19 Sep 2022 Mingqi Yuan, Bo Li, Xin Jin, Wenjun Zeng

Exploration is critical for deep reinforcement learning in complex environments with high-dimensional observations and sparse rewards.

Atari Games Benchmarking +3

Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability

no code implementations16 Sep 2022 Mengdi Xu, Zuxin Liu, Peide Huang, Wenhao Ding, Zhepeng Cen, Bo Li, Ding Zhao

A trustworthy reinforcement learning algorithm should be competent in solving challenging real-world problems, including {robustly} handling uncertainties, satisfying {safety} constraints to avoid catastrophic failures, and {generalizing} to unseen scenarios during deployments.

reinforcement-learning Reinforcement Learning (RL)

Graph Contrastive Learning with Personalized Augmentation

no code implementations14 Sep 2022 Xin Zhang, Qiaoyu Tan, Xiao Huang, Bo Li

Thus, blindly augmenting all graphs without considering their individual characteristics may undermine the performance of GCL arts. To deal with this, we propose the first principled framework, termed as \textit{G}raph contrastive learning with \textit{P}ersonalized \textit{A}ugmentation (GPA), to advance conventional GCL by allowing each graph to choose its own suitable augmentation operations. In essence, GPA infers tailored augmentation strategies for each graph based on its topology and node attributes via a learnable augmentation selector, which is a plug-and-play module and can be effectively trained with downstream GCL models end-to-end.

Contrastive Learning Data Augmentation

Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification

no code implementations13 Sep 2022 Chao Zhang, Bo Li, Tara Sainath, Trevor Strohman, Sepand Mavandadi, Shuo-Yiin Chang, Parisa Haghani

Language identification is critical for many downstream tasks in automatic speech recognition (ASR), and is beneficial to integrate into multilingual end-to-end ASR as an additional task.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

CARE: Certifiably Robust Learning with Reasoning via Variational Inference

1 code implementation12 Sep 2022 Jiawei Zhang, Linyi Li, Ce Zhang, Bo Li

In particular, we propose a certifiably robust learning with reasoning pipeline (CARE), which consists of a learning component and a reasoning component.

Variational Inference

Privacy of Autonomous Vehicles: Risks, Protection Methods, and Future Directions

no code implementations8 Sep 2022 Chulin Xie, Zhong Cao, Yunhui Long, Diange Yang, Ding Zhao, Bo Li

However, training AVs usually requires a large amount of training data collected from different driving environments (e. g., cities) as well as different types of personal information (e. g., working hours and routes).

Autonomous Vehicles

Uncovering the Connection Between Differential Privacy and Certified Robustness of Federated Learning against Poisoning Attacks

no code implementations8 Sep 2022 Chulin Xie, Yunhui Long, Pin-Yu Chen, Bo Li

We then provide two robustness certification criteria: certified prediction and certified attack cost for DPFL on both levels.

Federated Learning

Synergistic Redundancy: Towards Verifiable Safety for Autonomous Vehicles

no code implementations4 Sep 2022 Ayoosh Bansal, Simon Yu, Hunmin Kim, Bo Li, Naira Hovakimyan, Marco Caccamo, Lui Sha

The synergistic safety layer uses only verifiable and logically analyzable software to fulfill its tasks.

Autonomous Driving

Federated Learning with Label Distribution Skew via Logits Calibration

1 code implementation1 Sep 2022 Jie Zhang, Zhiqi Li, Bo Li, Jianghe Xu, Shuang Wu, Shouhong Ding, Chao Wu

Extensive experiments on federated datasets and real-world datasets demonstrate that FedLC leads to a more accurate global model and much improved performance.

Federated Learning

Verifiable Obstacle Detection

1 code implementation30 Aug 2022 Ayoosh Bansal, Hunmin Kim, Simon Yu, Bo Li, Naira Hovakimyan, Marco Caccamo, Lui Sha

Perception of obstacles remains a critical safety concern for autonomous vehicles.

Autonomous Driving

SphereDepth: Panorama Depth Estimation from Spherical Domain

no code implementations29 Aug 2022 Qingsong Yan, Qiang Wang, Kaiyong Zhao, Bo Li, Xiaowen Chu, Fei Deng

The panorama image can simultaneously demonstrate complete information of the surrounding environment and has many advantages in virtual tourism, games, robotics, etc.

Depth Estimation

Streaming Intended Query Detection using E2E Modeling for Continued Conversation

no code implementations29 Aug 2022 Shuo-Yiin Chang, Guru Prakash, Zelin Wu, Qiao Liang, Tara N. Sainath, Bo Li, Adam Stambler, Shyam Upadhyay, Manaal Faruqui, Trevor Strohman

In voice-enabled applications, a predetermined hotword isusually used to activate a device in order to attend to the query. However, speaking queries followed by a hotword each timeintroduces a cognitive burden in continued conversations.

Turn-Taking Prediction for Natural Conversational Speech

no code implementations29 Aug 2022 Shuo-Yiin Chang, Bo Li, Tara N. Sainath, Chao Zhang, Trevor Strohman, Qiao Liang, Yanzhang He

This makes doing speech recognition with conversational speech, including one with multiple queries, a challenging task.

speech-recognition Speech Recognition

Learning Instrumental Variable from Data Fusion for Treatment Effect Estimation

1 code implementation23 Aug 2022 Anpeng Wu, Kun Kuang, Ruoxuan Xiong, Minqing Zhu, Yuxuan Liu, Bo Li, Furui Liu, Zhihua Wang, Fei Wu

The advent of the big data era brought new opportunities and challenges to draw treatment effect in data fusion, that is, a mixed dataset collected from multiple sources (each source with an independent treatment assignment mechanism).


General Cutting Planes for Bound-Propagation-Based Neural Network Verification

2 code implementations11 Aug 2022 huan zhang, Shiqi Wang, Kaidi Xu, Linyi Li, Bo Li, Suman Jana, Cho-Jui Hsieh, J. Zico Kolter

Our generalized bound propagation method, GCP-CROWN, opens up the opportunity to apply general cutting plane methods for neural network verification while benefiting from the efficiency and GPU acceleration of bound propagation methods.

Understanding the stochastic dynamics of sequential decision-making processes: A path-integral analysis of Multi-armed Bandits

no code implementations11 Aug 2022 Bo Li, Chi Ho Yeung

In this paper, we employ techniques in statistical physics to analyze the MAB model, which facilitates to characterize the distribution of cumulative regrets at a finite short time, the central quantity of interest in an MAB algorithm, as well as the intricate dynamical behaviours of the model.

Decision Making Decision Making Under Uncertainty +1

An Empirical Exploration of Cross-domain Alignment between Language and Electroencephalogram

1 code implementation10 Aug 2022 William Han, JieLin Qiu, Jiacheng Zhu, Mengdi Xu, Douglas Weber, Bo Li, Ding Zhao

In addition, we provide interpretations of the performance improvement by: (1) visualizing the original feature distribution and the transformed feature distribution, showing the effectiveness of the alignment module for discovering and encoding the relationship between EEG and language; (2) visualizing word-level and sentence-level EEG-language alignment weights, showing the influence of different language semantics as well as EEG frequency features; and (3) visualizing brain topographical maps to provide an intuitive demonstration of the connectivity of EEG and language response in the brain regions.

Electroencephalogram (EEG) Sentiment Analysis

Large vocabulary speech recognition for languages of Africa: multilingual modeling and self-supervised learning

no code implementations5 Aug 2022 Sandy Ritchie, You-Chi Cheng, Mingqing Chen, Rajiv Mathews, Daan van Esch, Bo Li, Khe Chai Sim

Almost none of the 2, 000+ languages spoken in Africa have widely available automatic speech recognition systems, and the required data is also only available for a few languages.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

GeoECG: Data Augmentation via Wasserstein Geodesic Perturbation for Robust Electrocardiogram Prediction

no code implementations2 Aug 2022 Jiacheng Zhu, JieLin Qiu, Zhuolin Yang, Douglas Weber, Michael A. Rosenberg, Emerson Liu, Bo Li, Ding Zhao

In this paper, we propose a physiologically-inspired data augmentation method to improve performance and increase the robustness of heart disease detection based on ECG signals.

Data Augmentation

SecretGen: Privacy Recovery on Pre-Trained Models via Distribution Discrimination

1 code implementation25 Jul 2022 Zhuowen Yuan, Fan Wu, Yunhui Long, Chaowei Xiao, Bo Li

We first explore different statistical information which can discriminate the private training distribution from other distributions.

Model Selection Transfer Learning

FOCUS: Fairness via Agent-Awareness for Federated Learning on Heterogeneous Data

no code implementations21 Jul 2022 Wenda Chu, Chulin Xie, Boxin Wang, Linyi Li, Lang Yin, Han Zhao, Bo Li

However, due to the heterogeneous nature of local data, it is challenging to optimize or even define fairness of the trained global model for the agents.

Fairness Federated Learning

Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMM

no code implementations20 Jul 2022 Chulin Xie, Pin-Yu Chen, Ce Zhang, Bo Li

Moreover, we show that a byproduct of our framework is that the weights of learned linear heads reflect the importance of local clients.

Denoising Federated Learning +1

Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning

1 code implementation19 Jul 2022 Wenhao Ding, Haohong Lin, Bo Li, Ding Zhao

As a pivotal component to attaining generalizable solutions in human intelligence, reasoning provides great potential for reinforcement learning (RL) agents' generalization towards varied goals by summarizing part-to-whole arguments and discovering cause-and-effect relations.

Causal Discovery reinforcement-learning +1

Is Vertical Logistic Regression Privacy-Preserving? A Comprehensive Privacy Analysis and Beyond

no code implementations19 Jul 2022 Yuzheng Hu, Tianle Cai, Jinyong Shan, Shange Tang, Chaochao Cai, Ethan Song, Bo Li, Dawn Song

We provide a comprehensive and rigorous privacy analysis of VLR in a class of open-source Federated Learning frameworks, where the protocols might differ between one another, yet a procedure of obtaining local gradients is implicitly shared.

Federated Learning Philosophy +2

Game of Trojans: A Submodular Byzantine Approach

no code implementations13 Jul 2022 Dinuka Sahabandu, Arezoo Rajabi, Luyao Niu, Bo Li, Bhaskar Ramasubramanian, Radha Poovendran

The results show that (i) with Submodular Trojan algorithm, the adversary needs to embed a Trojan trigger into a very small fraction of samples to achieve high accuracy on both Trojan and clean samples, and (ii) the MM Trojan algorithm yields a trained Trojan model that evades detection with probability 1.

Scalable K-FAC Training for Deep Neural Networks with Distributed Preconditioning

1 code implementation30 Jun 2022 Lin Zhang, Shaohuai Shi, Wei Wang, Bo Li

The second-order optimization methods, notably the D-KFAC (Distributed Kronecker Factored Approximate Curvature) algorithms, have gained traction on accelerating deep neural network (DNN) training on GPU clusters.

How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection

1 code implementation28 Jun 2022 Mantas Mazeika, Bo Li, David Forsyth

To meet these challenges, we present a new approach to model stealing defenses called gradient redirection.

Pisces: Efficient Federated Learning via Guided Asynchronous Training

no code implementations18 Jun 2022 Zhifeng Jiang, Wei Wang, Baochun Li, Bo Li

Current FL systems employ a participant selection strategy to select fast clients with quality data in each iteration.

Federated Learning Navigate

Double Sampling Randomized Smoothing

1 code implementation16 Jun 2022 Linyi Li, Jiawei Zhang, Tao Xie, Bo Li

To overcome this hurdle, we propose a Double Sampling Randomized Smoothing (DSRS) framework, which exploits the sampled probability from an additional smoothing distribution to tighten the robustness certification of the previous smoothed classifier.

Can pruning improve certified robustness of neural networks?

1 code implementation15 Jun 2022 Zhangheng Li, Tianlong Chen, Linyi Li, Bo Li, Zhangyang Wang

Given the fact that neural networks are often over-parameterized, one effective way to reduce such computational overhead is neural network pruning, by removing redundant parameters from trained neural networks.

Network Pruning

Sparse Mixture-of-Experts are Domain Generalizable Learners

1 code implementation8 Jun 2022 Bo Li, Yifei Shen, Jingkang Yang, Yezhen Wang, Jiawei Ren, Tong Che, Jun Zhang, Ziwei Liu

It is motivated by an empirical finding that transformer-based models trained with empirical risk minimization (ERM) outperform CNN-based models employing state-of-the-art (SOTA) DG algorithms on multiple DG datasets.

Ranked #7 on Domain Generalization on DomainNet (using extra training data)

Domain Generalization Object Recognition

Distributionally Invariant Learning: Rationalization and Practical Algorithms

no code implementations7 Jun 2022 Jiashuo Liu, Jiayun Wu, Jie Peng, Zheyan Shen, Bo Li, Peng Cui

We reformulate the invariant learning problem under latent heterogeneity into a relaxed form that pursues the distributional invariance, based on which we propose our novel Distributionally Invariant Learning (DIL) framework as well as two implementations named DIL-MMD and DIL-KL.

Towards Practical Differential Privacy in Data Analysis: Understanding the Effect of Epsilon on Utility in Private ERM

no code implementations6 Jun 2022 Yuzhe Li, Yong liu, Bo Li, Weiping Wang, Nan Liu

In this paper, we focus our attention on private Empirical Risk Minimization (ERM), which is one of the most commonly used data analysis method.

Certifying Some Distributional Fairness with Subpopulation Decomposition

1 code implementation31 May 2022 Mintong Kang, Linyi Li, Maurice Weber, Yang Liu, Ce Zhang, Bo Li

In this paper, we first formulate the certified fairness of an ML model trained on a given data distribution as an optimization problem based on the model performance loss bound on a fairness constrained distribution, which is within bounded distributional distance with the training distribution.


On the Robustness of Safe Reinforcement Learning under Observational Perturbations

1 code implementation29 May 2022 Zuxin Liu, Zijian Guo, Zhepeng Cen, huan zhang, Jie Tan, Bo Li, Ding Zhao

One interesting and counter-intuitive finding is that the maximum reward attack is strong, as it can both induce unsafe behaviors and make the attack stealthy by maintaining the reward.

Adversarial Attack reinforcement-learning +2

Efficient Federated Learning with Spike Neural Networks for Traffic Sign Recognition

no code implementations28 May 2022 Kan Xie, Zhe Zhang, Bo Li, Jiawen Kang, Dusit Niyato, Shengli Xie, Yi Wu

However, for machine learning-based traffic sign recognition on the Internet of Vehicles (IoV), a large amount of traffic sign data from distributed vehicles is needed to be gathered in a centralized server for model training, which brings serious privacy leakage risk because of traffic sign data containing lots of location privacy information.

Federated Learning Privacy Preserving +1

VeriFi: Towards Verifiable Federated Unlearning

no code implementations25 May 2022 Xiangshan Gao, Xingjun Ma, Jingyi Wang, Youcheng Sun, Bo Li, Shouling Ji, Peng Cheng, Jiming Chen

One desirable property for FL is the implementation of the right to be forgotten (RTBF), i. e., a leaving participant has the right to request to delete its private data from the global model.

Federated Learning

BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models

1 code implementation16 May 2022 Bo Li, Kaitao Xue, Bin Liu, Yu-Kun Lai

In this paper, a novel image-to-image translation method based on the Brownian Bridge Diffusion Model (BBDM) is proposed, which models image-to-image translation as a stochastic Brownian bridge process, and learns the translation between two domains directly through the bidirectional diffusion process rather than a conditional generation process.

Image-to-Image Translation Translation

SemAttack: Natural Textual Attacks via Different Semantic Spaces

1 code implementation Findings (NAACL) 2022 Boxin Wang, Chejian Xu, Xiangyu Liu, Yu Cheng, Bo Li

In particular, SemAttack optimizes the generated perturbations constrained on generic semantic spaces, including typo space, knowledge space (e. g., WordNet), contextualized semantic space (e. g., the embedding space of BERT clusterings), or the combination of these spaces.

Adversarial Text

Cross Domain Object Detection by Target-Perceived Dual Branch Distillation

1 code implementation CVPR 2022 Mengzhe He, Yali Wang, Jiaxi Wu, Yiru Wang, Hanqing Li, Bo Li, Weihao Gan, Wei Wu, Yu Qiao

It can adaptively enhance source detector to perceive objects in a target image, by leveraging target proposal contexts from iterative cross-attention.

object-detection Object Detection

Data Debugging with Shapley Importance over End-to-End Machine Learning Pipelines

1 code implementation23 Apr 2022 Bojan Karlaš, David Dao, Matteo Interlandi, Bo Li, Sebastian Schelter, Wentao Wu, Ce Zhang

We present DataScope (ease. ml/datascope), the first system that efficiently computes Shapley values of training examples over an end-to-end ML pipeline, and illustrate its applications in data debugging for ML training.

BIG-bench Machine Learning Fairness

Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond

1 code implementation18 Apr 2022 Haoxiang Wang, Bo Li, Han Zhao

Gradual domain adaptation (GDA), on the other hand, assumes a path of $(T-1)$ unlabeled intermediate domains bridging the source and target, and aims to provide better generalization in the target domain by leveraging the intermediate ones.

Unsupervised Domain Adaptation

Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection

no code implementations CVPR 2022 Jiaxi Wu, Jiaxin Chen, Mengzhe He, Yiru Wang, Bo Li, Bingqi Ma, Weihao Gan, Wei Wu, Yali Wang, Di Huang

Specifically, TRKP adopts the teacher-student framework, where the multi-head teacher network is built to extract knowledge from labeled source domains and guide the student network to learn detectors in unlabeled target domain.

Disentanglement Domain Adaptation +2

MHMS: Multimodal Hierarchical Multimedia Summarization

no code implementations7 Apr 2022 JieLin Qiu, Jiacheng Zhu, Mengdi Xu, Franck Dernoncourt, Trung Bui, Zhaowen Wang, Bo Li, Ding Zhao, Hailin Jin

Multimedia summarization with multimodal output can play an essential role in real-world applications, i. e., automatically generating cover images and titles for news articles or providing introductions to online videos.

Unsupervised Learning of Accurate Siamese Tracking

1 code implementation CVPR 2022 Qiuhong Shen, Lei Qiao, Jinyang Guo, Peixia Li, Xin Li, Bo Li, Weitao Feng, Weihao Gan, Wei Wu, Wanli Ouyang

As unlimited self-supervision signals can be obtained by tracking a video along a cycle in time, we investigate evolving a Siamese tracker by tracking videos forward-backward.

Visual Object Tracking

Test Against High-Dimensional Uncertainties: Accelerated Evaluation of Autonomous Vehicles with Deep Importance Sampling

no code implementations4 Apr 2022 Mansur Arief, Zhepeng Cen, Zhenyuan Liu, Zhiyuang Huang, Henry Lam, Bo Li, Ding Zhao

In this work, we present Deep Importance Sampling (Deep IS) framework that utilizes a deep neural network to obtain an efficient IS that is on par with the state-of-the-art, capable of reducing the required sample size 43 times smaller than the naive sampling method to achieve 10% relative error and while producing an estimate that is much less conservative.

Autonomous Vehicles

A thermoelectric generation system using waste heat recovery from petrochemical pipeline to power wireless sensor

no code implementations29 Mar 2022 Bo Li, Xiao-Liang Guo, Yu-Tao Li

This work describes a thermoelectric generation system with an optimized heat sink for wireless monitoring sensor power supply at high temperature.

PhysioMTL: Personalizing Physiological Patterns using Optimal Transport Multi-Task Regression

1 code implementation19 Mar 2022 Jiacheng Zhu, Gregory Darnell, Agni Kumar, Ding Zhao, Bo Li, XuanLong Nguyen, Shirley You Ren

The proposed method learns an individual-specific predictive model from heterogeneous observations, and enables estimation of an optimal transport map that yields a push forward operation onto the demographic features for each task.

Heart Rate Variability regression

Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning

1 code implementation CVPR 2022 Haoxiang Wang, Yite Wang, Ruoyu Sun, Bo Li

We show that the performance of MetaNTK-NAS is comparable or better than the state-of-the-art NAS method designed for few-shot learning while enjoying more than 100x speedup.

Few-Shot Learning Neural Architecture Search

COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks

1 code implementation ICLR 2022 Fan Wu, Linyi Li, Chejian Xu, huan zhang, Bhavya Kailkhura, Krishnaram Kenthapadi, Ding Zhao, Bo Li

We leverage COPA to certify three RL environments trained with different algorithms and conclude: (1) The proposed robust aggregation protocols such as temporal aggregation can significantly improve the certifications; (2) Our certification for both per-state action stability and cumulative reward bound are efficient and tight; (3) The certification for different training algorithms and environments are different, implying their intrinsic robustness properties.

Offline RL reinforcement-learning +1

Towards Practical Certifiable Patch Defense with Vision Transformer

no code implementations CVPR 2022 Zhaoyu Chen, Bo Li, Jianghe Xu, Shuang Wu, Shouhong Ding, Wenqiang Zhang

To move towards a practical certifiable patch defense, we introduce Vision Transformer (ViT) into the framework of Derandomized Smoothing (DS).

The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining

no code implementations14 Mar 2022 Yi Liu, Lei Xu, Xingliang Yuan, Cong Wang, Bo Li

Existing machine unlearning techniques focus on centralized training, where access to all holders' training data is a must for the server to conduct the unlearning process.

Federated Learning

Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking

1 code implementation10 Mar 2022 BoYu Chen, Peixia Li, Lei Bai, Lei Qiao, Qiuhong Shen, Bo Li, Weihao Gan, Wei Wu, Wanli Ouyang

Exploiting a general-purpose neural architecture to replace hand-wired designs or inductive biases has recently drawn extensive interest.

Visual Object Tracking

Machine Learning Empowered Intelligent Data Center Networking: A Survey

no code implementations28 Feb 2022 Bo Li, Ting Wang, Peng Yang, Mingsong Chen, Shui Yu, Mounir Hamdi

To support the needs of ever-growing cloud-based services, the number of servers and network devices in data centers is increasing exponentially, which in turn results in high complexities and difficulties in network optimization.

BIG-bench Machine Learning Management

Raman Spectrum Matching with Contrastive Representation Learning

no code implementations25 Feb 2022 Bo Li, Mikkel N. Schmidt, Tommy S. Alstrøm

We propose a new machine learning technique for Raman spectrum matching, based on contrastive representation learning, that requires no preprocessing and works with as little as a single reference spectrum from each class.

BIG-bench Machine Learning Conformal Prediction +1

CAKE: A Scalable Commonsense-Aware Framework For Multi-View Knowledge Graph Completion

1 code implementation ACL 2022 Guanglin Niu, Bo Li, Yongfei Zhang, ShiLiang Pu

The previous knowledge graph embedding (KGE) techniques suffer from invalid negative sampling and the uncertainty of fact-view link prediction, limiting KGC's performance.

Knowledge Graph Embedding Link Prediction

Regulatory Instruments for Fair Personalized Pricing

1 code implementation9 Feb 2022 Renzhe Xu, Xingxuan Zhang, Peng Cui, Bo Li, Zheyan Shen, Jiazheng Xu

Personalized pricing is a business strategy to charge different prices to individual consumers based on their characteristics and behaviors.

Multi-model Ensemble Analysis with Neural Network Gaussian Processes

no code implementations8 Feb 2022 Trevor Harris, Bo Li, Ryan Sriver

Multi-model ensemble analysis integrates information from multiple climate models into a unified projection.


Certifying Out-of-Domain Generalization for Blackbox Functions

1 code implementation3 Feb 2022 Maurice Weber, Linyi Li, Boxin Wang, Zhikuan Zhao, Bo Li, Ce Zhang

As a result, the wider application of these techniques is currently limited by its scalability and flexibility -- these techniques often do not scale to large-scale datasets with modern deep neural networks or cannot handle loss functions which may be non-smooth such as the 0-1 loss.

Domain Generalization

Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularization

no code implementations3 Feb 2022 Xiaojun Xu, Jacky Yibo Zhang, Evelyn Ma, Danny Son, Oluwasanmi Koyejo, Bo Li

We propose a general theoretical framework proving that factors involving the model function class regularization are sufficient conditions for relative domain transferability.

Domain Generalization

TPC: Transformation-Specific Smoothing for Point Cloud Models

1 code implementation30 Jan 2022 Wenda Chu, Linyi Li, Bo Li

In this paper, we propose a transformation-specific smoothing framework TPC, which provides tight and scalable robustness guarantees for point cloud models against semantic transformation attacks.

Autonomous Vehicles

Provable Domain Generalization via Invariant-Feature Subspace Recovery

1 code implementation30 Jan 2022 Haoxiang Wang, Haozhe Si, Bo Li, Han Zhao

Our first algorithm, ISR-Mean, can identify the subspace spanned by invariant features from the first-order moments of the class-conditional distributions, and achieve provable domain generalization with $d_s+1$ training environments under the data model of Rosenfeld et al. (2021).

Domain Generalization

Constrained Variational Policy Optimization for Safe Reinforcement Learning

1 code implementation28 Jan 2022 Zuxin Liu, Zhepeng Cen, Vladislav Isenbaev, Wei Liu, Zhiwei Steven Wu, Bo Li, Ding Zhao

Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications.

reinforcement-learning Reinforcement Learning (RL) +1

Improving the fusion of acoustic and text representations in RNN-T

no code implementations25 Jan 2022 Chao Zhang, Bo Li, Zhiyun Lu, Tara N. Sainath, Shuo-Yiin Chang

The recurrent neural network transducer (RNN-T) has recently become the mainstream end-to-end approach for streaming automatic speech recognition (ASR).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Which Style Makes Me Attractive? Interpretable Control Discovery and Counterfactual Explanation on StyleGAN

1 code implementation24 Jan 2022 Bo Li, Qiulin Wang, JiQuan Pei, Yu Yang, Xiangyang Ji

First, we propose a novel approach to disentangle latent subspace semantics by exploiting existing face analysis models, e. g., face parsers and face landmark detectors.

Counterfactual Explanation Disentanglement +2

Dual Perceptual Loss for Single Image Super-Resolution Using ESRGAN

no code implementations17 Jan 2022 Jie Song, Huawei Yi, Wenqian Xu, Xiaohui Li, Bo Li, Yuanyuan Liu

The proposal of perceptual loss solves the problem that per-pixel difference loss function causes the reconstructed image to be overly-smooth, which acquires a significant progress in the field of single image super-resolution reconstruction.

Image Super-Resolution

Equalized Focal Loss for Dense Long-Tailed Object Detection

1 code implementation CVPR 2022 Bo Li, Yongqiang Yao, Jingru Tan, Gang Zhang, Fengwei Yu, Jianwei Lu, Ye Luo

The conventional focal loss balances the training process with the same modulating factor for all categories, thus failing to handle the long-tailed problem.

object-detection Object Detection

Towards Efficient Data Free Black-Box Adversarial Attack

1 code implementation CVPR 2022 Jie Zhang, Bo Li, Jianghe Xu, Shuang Wu, Shouhong Ding, Lei Zhang, Chao Wu

The proposed method can efficiently imitate the target model through a small number of queries and achieve high attack success rate.

Adversarial Attack

Efficient Multi-View Stereo by Iterative Dynamic Cost Volume

1 code implementation CVPR 2022 Shaoqian Wang, Bo Li, Yuchao Dai

Specifically, a lightweight 3D CNN is utilized to generate the coarsest initial depth map which is essential to launch the GRU and guarantee a fast convergence.

Detecting Camouflaged Object in Frequency Domain

1 code implementation CVPR 2022 Yijie Zhong, Bo Li, Lv Tang, Senyun Kuang, Shuang Wu, Shouhong Ding

We first design a novel frequency enhancement module (FEM) to dig clues of camouflaged objects in the frequency domain.

object-detection Object Detection

DENSE: Data-Free One-Shot Federated Learning

1 code implementation23 Dec 2021 Jie Zhang, Chen Chen, Bo Li, Lingjuan Lyu, Shuang Wu, Shouhong Ding, Chunhua Shen, Chao Wu

One-shot Federated Learning (FL) has recently emerged as a promising approach, which allows the central server to learn a model in a single communication round.

Federated Learning

Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification

1 code implementation15 Dec 2021 Xiaohua Chen, Yucan Zhou, Dayan Wu, Wanqian Zhang, Yu Zhou, Bo Li, Weiping Wang

Since the covariance matrix of each category represents the feature transformation directions, we can sample new directions from similar categories to generate definitely different instances.

Data Augmentation Long-tail Learning

PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures

2 code implementations CVPR 2022 Dan Hendrycks, Andy Zou, Mantas Mazeika, Leonard Tang, Bo Li, Dawn Song, Jacob Steinhardt

In real-world applications of machine learning, reliable and safe systems must consider measures of performance beyond standard test set accuracy.

Adversarial Robustness Anomaly Detection +1

Perform Like an Engine: A Closed-Loop Neural-Symbolic Learning Framework for Knowledge Graph Inference

no code implementations COLING 2022 Guanglin Niu, Bo Li, Yongfei Zhang, ShiLiang Pu

Knowledge graph (KG) inference aims to address the natural incompleteness of KGs, including rule learning-based and KG embedding (KGE) models.

Association Link Prediction

Integrated Latent Heterogeneity and Invariance Learning in Kernel Space

no code implementations NeurIPS 2021 Jiashuo Liu, Zheyuan Hu, Peng Cui, Bo Li, Zheyan Shen

The ability to generalize under distributional shifts is essential to reliable machine learning, while models optimized with empirical risk minimization usually fail on non-$i. i. d$ testing data.

Fair Scheduling for Time-dependent Resources

no code implementations NeurIPS 2021 Bo Li, Minming Li, Ruilong Zhang

We study a fair resource scheduling problem, where a set of interval jobs are to be allocated to heterogeneous machines controlled by intellectual agents. Each job is associated with release time, deadline, and processing time such that it can be processed if its complete processing period is between its release time and deadline.

Fairness Scheduling

Towards Efficiently Evaluating the Robustness of Deep Neural Networks in IoT Systems: A GAN-based Method

no code implementations19 Nov 2021 Tao Bai, Jun Zhao, Jinlin Zhu, Shoudong Han, Jiefeng Chen, Bo Li, Alex Kot

Through extensive experiments, AI-GAN achieves high attack success rates, outperforming existing methods, and reduces generation time significantly.

Joint Unsupervised and Supervised Training for Multilingual ASR

no code implementations15 Nov 2021 Junwen Bai, Bo Li, Yu Zhang, Ankur Bapna, Nikhil Siddhartha, Khe Chai Sim, Tara N. Sainath

Our average WER of all languages outperforms average monolingual baseline by 33. 3%, and the state-of-the-art 2-stage XLSR by 32%.

Language Modelling Masked Language Modeling +3

SAFA: Structure Aware Face Animation

1 code implementation9 Nov 2021 Qiulin Wang, Lu Zhang, Bo Li

On the other hand, some area of the generated image might be occluded in the source image, which makes it difficult for GAN to generate realistic appearance.

Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models

no code implementations4 Nov 2021 Boxin Wang, Chejian Xu, Shuohang Wang, Zhe Gan, Yu Cheng, Jianfeng Gao, Ahmed Hassan Awadallah, Bo Li

In this paper, we present Adversarial GLUE (AdvGLUE), a new multi-task benchmark to quantitatively and thoroughly explore and evaluate the vulnerabilities of modern large-scale language models under various types of adversarial attacks.

Adversarial Attack Adversarial Robustness +1

CausalAF: Causal Autoregressive Flow for Safety-Critical Driving Scenario Generation

no code implementations26 Oct 2021 Wenhao Ding, Haohong Lin, Bo Li, Ding Zhao

Generating safety-critical scenarios, which are crucial yet difficult to collect, provides an effective way to evaluate the robustness of autonomous driving systems.

Autonomous Driving Scene Generation

What Would Jiminy Cricket Do? Towards Agents That Behave Morally

1 code implementation25 Oct 2021 Dan Hendrycks, Mantas Mazeika, Andy Zou, Sahil Patel, Christine Zhu, Jesus Navarro, Dawn Song, Bo Li, Jacob Steinhardt

When making everyday decisions, people are guided by their conscience, an internal sense of right and wrong.

Highly Efficient Natural Image Matting

no code implementations25 Oct 2021 Yijie Zhong, Bo Li, Lv Tang, Hao Tang, Shouhong Ding

With a lightweight basic convolution block, we build a two-stages framework: Segmentation Network (SN) is designed to capture sufficient semantics and classify the pixels into unknown, foreground and background regions; Matting Refine Network (MRN) aims at capturing detailed texture information and regressing accurate alpha values.

Image Matting

Kernelized Heterogeneous Risk Minimization

1 code implementation24 Oct 2021 Jiashuo Liu, Zheyuan Hu, Peng Cui, Bo Li, Zheyan Shen

The ability to generalize under distributional shifts is essential to reliable machine learning, while models optimized with empirical risk minimization usually fail on non-$i. i. d$ testing data.

Anti-Backdoor Learning: Training Clean Models on Poisoned Data

1 code implementation NeurIPS 2021 Yige Li, Xixiang Lyu, Nodens Koren, Lingjuan Lyu, Bo Li, Xingjun Ma

From this view, we identify two inherent characteristics of backdoor attacks as their weaknesses: 1) the models learn backdoored data much faster than learning with clean data, and the stronger the attack the faster the model converges on backdoored data; 2) the backdoor task is tied to a specific class (the backdoor target class).

Backdoor Attack

Trustworthy AI: From Principles to Practices

no code implementations4 Oct 2021 Bo Li, Peng Qi, Bo Liu, Shuai Di, Jingen Liu, JiQuan Pei, JinFeng Yi, BoWen Zhou

In this review, we provide AI practitioners with a comprehensive guide for building trustworthy AI systems.


CARD: Certifiably Robust Machine Learning Pipeline via Domain Knowledge Integration

no code implementations29 Sep 2021 Jiawei Zhang, Linyi Li, Bo Li

In particular, we express the domain knowledge as first-order logic rules and embed these logic rules in a probabilistic graphical model.

BIG-bench Machine Learning

I-PGD-AT: Efficient Adversarial Training via Imitating Iterative PGD Attack

no code implementations29 Sep 2021 Xiaosen Wang, Bhavya Kailkhura, Krishnaram Kenthapadi, Bo Li

Finally, to demonstrate the generality of I-PGD-AT, we integrate it into PGD adversarial training and show that it can even further improve the robustness.

Certified Robustness for Free in Differentially Private Federated Learning

no code implementations29 Sep 2021 Chulin Xie, Yunhui Long, Pin-Yu Chen, Krishnaram Kenthapadi, Bo Li

Federated learning (FL) provides an efficient training paradigm to jointly train a global model leveraging data from distributed users.

Federated Learning

RVFR: Robust Vertical Federated Learning via Feature Subspace Recovery

no code implementations29 Sep 2021 Jing Liu, Chulin Xie, Krishnaram Kenthapadi, Oluwasanmi O Koyejo, Bo Li

Vertical Federated Learning (VFL) is a distributed learning paradigm that allows multiple agents to jointly train a global model when each agent holds a different subset of features for the same sample(s).

Federated Learning

DOODLER: Determining Out-Of-Distribution Likelihood from Encoder Reconstructions

no code implementations27 Sep 2021 Jonathan S. Kent, Bo Li

Deep Learning models possess two key traits that, in combination, make their use in the real world a risky prospect.

Out of Distribution (OOD) Detection

Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategies

no code implementations9 Sep 2021 Zhifeng Jiang, Wei Wang, Bo Li, Qiang Yang

The increasing demand for privacy-preserving collaborative learning has given rise to a new computing paradigm called federated learning (FL), in which clients collaboratively train a machine learning (ML) model without revealing their private training data.

Benchmarking Federated Learning +1

Eliciting Truthful Reports with Partial Signals in Repeated Games

no code implementations9 Sep 2021 Yutong Wu, Ali Khodabakhsh, Bo Li, Evdokia Nikolova, Emmanouil Pountourakis

Namely, besides charging the player the reported value, the mechanism charges a penalty proportional to her inconsistent reports.

Spatially and Robustly Hybrid Mixture Regression Model for Inference of Spatial Dependence

1 code implementation1 Sep 2021 Wennan Chang, Pengtao Dang, Changlin Wan, Xiaoyu Lu, Yue Fang, Tong Zhao, Yong Zang, Bo Li, Chi Zhang, Sha Cao

Compared with existing spatial regression models, our proposed model assumes the existence a few distinct regression models that are estimated based on observations that exhibit similar response-predictor relationships.


Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision

no code implementations30 Aug 2021 Bo Li, Xinyang Jiang, Donglin Bai, Yuge Zhang, Ningxin Zheng, Xuanyi Dong, Lu Liu, Yuqing Yang, Dongsheng Li

The energy consumption of deep learning models is increasing at a breathtaking rate, which raises concerns due to potential negative effects on carbon neutrality in the context of global warming and climate change.

Model Compression