Search Results for author: Bo Li

Found 299 papers, 104 papers with code

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

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

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.


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.

G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators

1 code implementation NeurIPS 2021 Yunhui Long, Boxin Wang, Zhuolin Yang, Bhavya Kailkhura, Aston Zhang, Carl Gunter, Bo Li

In particular, we train a student data generator with an ensemble of teacher discriminators and propose a novel private gradient aggregation mechanism to ensure differential privacy on all information that flows from teacher discriminators to the student generator.

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 Speech Recognition +1

SAFA: Structure Aware Face Animation

no code implementations9 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 +2

CausalAF: Causal Autoregressive Flow for Goal-Directed Safety-Critical Scenes Generation

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

Goal-directed generation, aiming for solving downstream tasks by generating diverse data, has a potentially wide range of applications in the real world.

Autonomous Vehicles 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).

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 strive to provide AI practitioners a comprehensive guide towards building trustworthy AI systems.


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.

Eliciting Information with Partial Signals in Repeated Games

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

We show how a combination of the penalty rate and the length of the game incentivizes the agent to be truthful for the entire game, a phenomenon we call "fear of tomorrow verification".

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

LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis

no code implementations14 Aug 2021 Fan Wu, Yunhui Long, Ce Zhang, Bo Li

We show that these DP GCN mechanisms are not always resilient against LinkTeller empirically under mild privacy guarantees ($\varepsilon>5$).

Recommendation Systems Traffic Prediction

Disentangled High Quality Salient Object Detection

2 code implementations ICCV 2021 Lv Tang, Bo Li, Shouhong Ding, Mofei Song

As a pixel-wise classification task, LRSCN is designed to capture sufficient semantics at low-resolution to identify the definite salient, background and uncertain image regions.

Object Detection Salient Object Detection

Energy-Based Open-World Uncertainty Modeling for Confidence Calibration

no code implementations ICCV 2021 Yezhen Wang, Bo Li, Tong Che, Kaiyang Zhou, Ziwei Liu, Dongsheng Li

Confidence calibration is of great importance to the reliability of decisions made by machine learning systems.

On the Certified Robustness for Ensemble Models and Beyond

no code implementations22 Jul 2021 Zhuolin Yang, Linyi Li, Xiaojun Xu, Bhavya Kailkhura, Tao Xie, Bo Li

Thus, to explore the conditions that guarantee to provide certifiably robust ensemble ML models, we first prove that diversified gradient and large confidence margin are sufficient and necessary conditions for certifiably robust ensemble models under the model-smoothness assumption.

Accelerating Distributed K-FAC with Smart Parallelism of Computing and Communication Tasks

no code implementations14 Jul 2021 Shaohuai Shi, Lin Zhang, Bo Li

Specifically, 1) we first characterize the performance bottlenecks of D-KFAC, 2) we design and implement a pipelining mechanism for Kronecker factors computation and communication with dynamic tensor fusion, and 3) we develop a load balancing placement for inverting multiple matrices on GPU clusters.

Auto IV: Counterfactual Prediction via Automatic Instrumental Variable Decomposition

no code implementations13 Jul 2021 Junkun Yuan, Anpeng Wu, Kun Kuang, Bo Li, Runze Wu, Fei Wu, Lanfen Lin

We also learn confounder representations by encouraging them to be relevant to both the treatment and the outcome.

Causal Inference

Distributionally Robust Learning with Stable Adversarial Training

no code implementations30 Jun 2021 Jiashuo Liu, Zheyan Shen, Peng Cui, Linjun Zhou, Kun Kuang, Bo Li

In this paper, we propose a novel Stable Adversarial Learning (SAL) algorithm that leverages heterogeneous data sources to construct a more practical uncertainty set and conduct differentiated robustness optimization, where covariates are differentiated according to the stability of their correlations with the target.

A Comprehensive Survey of Incentive Mechanism for Federated Learning

no code implementations27 Jun 2021 Rongfei Zeng, Chao Zeng, Xingwei Wang, Bo Li, Xiaowen Chu

Federated learning utilizes various resources provided by participants to collaboratively train a global model, which potentially address the data privacy issue of machine learning.

Federated Learning

MG-DVD: A Real-time Framework for Malware Variant Detection Based on Dynamic Heterogeneous Graph Learning

no code implementations23 Jun 2021 Chen Liu, Bo Li, Jun Zhao, Ming Su, Xu-Dong Liu

In this paper, we propose MG-DVD, a novel detection framework based on dynamic heterogeneous graph learning, to detect malware variants in real time.

Graph Learning

CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing

1 code implementation17 Jun 2021 Fan Wu, Linyi Li, Zijian Huang, Yevgeniy Vorobeychik, Ding Zhao, Bo Li

Next, we develop a global smoothing algorithm for certifying the robustness of a finite-horizon cumulative reward under adversarial state perturbations.

Atari Games

Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation

1 code implementation16 Jun 2021 Haoxiang Wang, Han Zhao, Bo Li

Despite the subtle difference between MTL and meta-learning in the problem formulation, both learning paradigms share the same insight that the shared structure between existing training tasks could lead to better generalization and adaptation.

Few-Shot Image Classification Meta-Learning +1

CRFL: Certifiably Robust Federated Learning against Backdoor Attacks

1 code implementation15 Jun 2021 Chulin Xie, Minghao Chen, Pin-Yu Chen, Bo Li

Our method exploits clipping and smoothing on model parameters to control the global model smoothness, which yields a sample-wise robustness certification on backdoors with limited magnitude.

Federated Learning

Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks

1 code implementation11 Jun 2021 Nezihe Merve Gürel, Xiangyu Qi, Luka Rimanic, Ce Zhang, Bo Li

In particular, we develop KEMLP by integrating a diverse set of weak auxiliary models based on their logical relationships to the main DNN model that performs the target task.

Invariant Information Bottleneck for Domain Generalization

no code implementations11 Jun 2021 Bo Li, Yifei Shen, Yezhen Wang, Wenzhen Zhu, Colorado J. Reed, Jun Zhang, Dongsheng Li, Kurt Keutzer, Han Zhao

The main challenge for domain generalization (DG) is to overcome the potential distributional shift between multiple training domains and unseen test domains.

Domain Generalization

Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation

1 code implementation10 Jun 2021 Jiawei Zhang, Linyi Li, Huichen Li, Xiaolu Zhang, Shuang Yang, Bo Li

In this paper, we show that such efficiency highly depends on the scale at which the attack is applied, and attacking at the optimal scale significantly improves the efficiency.

Face Recognition

Robustifying Reinforcement Learning Policies with $\mathcal{L}_1$ Adaptive Control

no code implementations4 Jun 2021 Yikun Cheng, Pan Zhao, Manan Gandhi, Bo Li, Evangelos Theodorou, Naira Hovakimyan

A reinforcement learning (RL) policy trained in a nominal environment could fail in a new/perturbed environment due to the existence of dynamic variations.

PSGAN++: Robust Detail-Preserving Makeup Transfer and Removal

1 code implementation26 May 2021 Si Liu, Wentao Jiang, Chen Gao, Ran He, Jiashi Feng, Bo Li, Shuicheng Yan

In this paper, we address the makeup transfer and removal tasks simultaneously, which aim to transfer the makeup from a reference image to a source image and remove the makeup from the with-makeup image respectively.

Style Transfer

Deep Kernel Gaussian Process Based Financial Market Predictions

no code implementations26 May 2021 Yong Shi, Wei Dai, Wen Long, Bo Li

However, the deep kernel Gaussian Process has not been applied to forecast the conditional returns and volatility in financial market to the best of our knowledge.

FILTRA: Rethinking Steerable CNN by Filter Transform

1 code implementation25 May 2021 Bo Li, Qili Wang, Gim Hee Lee

It has been an intuitive and widely used technique to construct a steerable filter by augmenting a filter with its transformed copies in the past decades, which is named as filter transform in this paper.

Human-centric Relation Segmentation: Dataset and Solution

no code implementations24 May 2021 Si Liu, Zitian Wang, Yulu Gao, Lejian Ren, Yue Liao, Guanghui Ren, Bo Li, Shuicheng Yan

For the above exemplar case, our HRS task produces results in the form of relation triplets <girl [left hand], hold, book> and exacts segmentation masks of the book, with which the robot can easily accomplish the grabbing task.

Language understanding

TRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness

no code implementations NeurIPS 2021 Zhuolin Yang, Linyi Li, Xiaojun Xu, Shiliang Zuo, Qian Chen, Pan Zhou, Benjamin I. P. Rubinstein, Ce Zhang, Bo Li

To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness.

Cross-Modal Progressive Comprehension for Referring Segmentation

1 code implementation15 May 2021 Si Liu, Tianrui Hui, Shaofei Huang, Yunchao Wei, Bo Li, Guanbin Li

In this paper, we propose a Cross-Modal Progressive Comprehension (CMPC) scheme to effectively mimic human behaviors and implement it as a CMPC-I (Image) module and a CMPC-V (Video) module to improve referring image and video segmentation models.

Referring Expression Segmentation Semantic Segmentation +2

Heterogeneous Risk Minimization

no code implementations9 May 2021 Jiashuo Liu, Zheyuan Hu, Peng Cui, Bo Li, Zheyan Shen

In this paper, we propose Heterogeneous Risk Minimization (HRM) framework to achieve joint learning of latent heterogeneity among the data and invariant relationship, which leads to stable prediction despite distributional shifts.

Scaling End-to-End Models for Large-Scale Multilingual ASR

no code implementations30 Apr 2021 Bo Li, Ruoming Pang, Tara N. Sainath, Anmol Gulati, Yu Zhang, James Qin, Parisa Haghani, W. Ronny Huang, Min Ma, Junwen Bai

Building ASR models across many languages is a challenging multi-task learning problem due to large variations and heavily unbalanced data.

Multi-Task Learning

TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness

1 code implementation NeurIPS 2021 Zhuolin Yang, Linyi Li, Xiaojun Xu, Shiliang Zuo, Qian Chen, Benjamin Rubinstein, Pan Zhou, Ce Zhang, Bo Li

To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness.

Reduced Dynamics and Control for an Autonomous Bicycle

no code implementations30 Mar 2021 Jiaming Xiong, Bo Li, Ruihan Yu, Daolin Ma, Wei Wang, Caishan Liu

In this paper, we propose the reduced model for the full dynamics of a bicycle and analyze its nonlinear behavior under a proportional control law for steering.

Self-Supervised Pretraining Improves Self-Supervised Pretraining

1 code implementation23 Mar 2021 Colorado J. Reed, Xiangyu Yue, Ani Nrusimha, Sayna Ebrahimi, Vivek Vijaykumar, Richard Mao, Bo Li, Shanghang Zhang, Devin Guillory, Sean Metzger, Kurt Keutzer, Trevor Darrell

Through experimentation on 16 diverse vision datasets, we show HPT converges up to 80x faster, improves accuracy across tasks, and improves the robustness of the self-supervised pretraining process to changes in the image augmentation policy or amount of pretraining data.

Image Augmentation

Multi-Robot Task Allocation -- Complexity and Approximation

no code implementations23 Mar 2021 Haris Aziz, Hau Chan, Ágnes Cseh, Bo Li, Fahimeh Ramezani, Chenhao Wang

Multi-robot task allocation is one of the most fundamental classes of problems in robotics and is crucial for various real-world robotic applications such as search, rescue and area exploration.

DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation

1 code implementation20 Mar 2021 Boxin Wang, Fan Wu, Yunhui Long, Luka Rimanic, Ce Zhang, Bo Li

In this paper, we aim to explore the power of generative models and gradient sparsity, and propose a scalable privacy-preserving generative model DATALENS.

Dimensionality Reduction

Understanding Robustness in Teacher-Student Setting: A New Perspective

no code implementations25 Feb 2021 Zhuolin Yang, Zhaoxi Chen, Tiffany Cai, Xinyun Chen, Bo Li, Yuandong Tian

Extensive experiments show that student specialization correlates strongly with model robustness in different scenarios, including student trained via standard training, adversarial training, confidence-calibrated adversarial training, and training with robust feature dataset.

Data Augmentation

Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks

1 code implementation25 Feb 2021 Huichen Li, Linyi Li, Xiaojun Xu, Xiaolu Zhang, Shuang Yang, Bo Li

We aim to bridge the gap between the two by investigating how to efficiently estimate gradient based on a projected low-dimensional space.

Pyramid scheme in stock market: a kind of financial market simulation

no code implementations3 Feb 2021 Yong Shi, Bo Li, Guangle Du

Artificial stock market simulation based on agent is an important means to study financial market.

Rescuing Deep Hashing from Dead Bits Problem

no code implementations1 Feb 2021 Shu Zhao, Dayan Wu, Yucan Zhou, Bo Li, Weiping Wang

The proposed gradient amplifier and error-aware quantization loss are compatible with a variety of deep hashing methods.

Image Retrieval Quantization

Interaction between optical pulse and tumor using finite element analysis

no code implementations19 Jan 2021 Xianlin Song, Ao Teng, Jianshuang Wei, Hao Chen, Yang Zhao, Jianheng Chen, Fangwei Liu, Qianxiang Wan, Guoning Huang, Lingfang Song, Aojie Zhao, Bo Li, Zihao Li, Qiming He, Jinhong Zhang

As a non-destructive biological tissue imaging technology, photoacoustic imaging has important application value in the field of biomedicine.

Biological Physics

What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space

no code implementations18 Jan 2021 Shihao Zhao, Xingjun Ma, Yisen Wang, James Bailey, Bo Li, Yu-Gang Jiang

In this paper, we focus on image classification and propose a method to visualize and understand the class-wise knowledge (patterns) learned by DNNs under three different settings including natural, backdoor and adversarial.

Image Classification

Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks

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

NAD utilizes a teacher network to guide the finetuning of the backdoored student network on a small clean subset of data such that the intermediate-layer attention of the student network aligns with that of the teacher network.

Robusta: Robust AutoML for Feature Selection via Reinforcement Learning

no code implementations15 Jan 2021 Xiaoyang Wang, Bo Li, Yibo Zhang, Bhavya Kailkhura, Klara Nahrstedt

However, these AutoML pipelines only focus on improving the learning accuracy of benign samples while ignoring the ML model robustness under adversarial attacks.

AutoML Feature Importance +1

ORDNet: Capturing Omni-Range Dependencies for Scene Parsing

no code implementations11 Jan 2021 Shaofei Huang, Si Liu, Tianrui Hui, Jizhong Han, Bo Li, Jiashi Feng, Shuicheng Yan

Our ORDNet is able to extract more comprehensive context information and well adapt to complex spatial variance in scene images.

Scene Parsing

Improved ACD-based financial trade durations prediction leveraging LSTM networks and Attention Mechanism

no code implementations7 Jan 2021 Yong Shi, Wei Dai, Wen Long, Bo Li

In the input sequence, the temporal positions which are more important for predicting the next duration can be efficiently highlighted via the added attention mechanism layer.

The First 3D Coronal Loop Model Heated by MHD Waves against Radiative Losses

no code implementations4 Jan 2021 Mijie Shi, Tom Van Doorsselaere, Mingzhe Guo, Konstantinos Karampelas, Bo Li, Patrick Antolin

In the quest to solve the long-standing coronal heating problem, it has been suggested half a century ago that coronal loops could be heated by waves.

Solar and Stellar Astrophysics

Can Shape Structure Features Improve Model Robustness Under Diverse Adversarial Settings?

no code implementations ICCV 2021 MingJie Sun, Zichao Li, Chaowei Xiao, Haonan Qiu, Bhavya Kailkhura, Mingyan Liu, Bo Li

Specifically, EdgeNetRob and EdgeGANRob first explicitly extract shape structure features from a given image via an edge detection algorithm.

Edge Detection

Fast Estimation for Privacy and Utility in Differentially Private Machine Learning

no code implementations1 Jan 2021 Yuzhe Li, Yong liu, Weipinng Wang, Bo Li, Nan Liu

In this paper, we deduce the influence of $\epsilon$ on utility private learning models through strict mathematical derivation, and propose a novel approximate approach for estimating the utility of any $\epsilon$ value.

Perturbation Type Categorization for Multiple $\ell_p$ Bounded Adversarial Robustness

no code implementations1 Jan 2021 Pratyush Maini, Xinyun Chen, Bo Li, Dawn Song

In addition, we demonstrate the realization of this trade-off in deep networks by adding random noise to the model input at test time, enabling enhanced robustness against strong adaptive attacks.

Adversarial Robustness

Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses

no code implementations18 Dec 2020 Micah Goldblum, Dimitris Tsipras, Chulin Xie, Xinyun Chen, Avi Schwarzschild, Dawn Song, Aleksander Madry, Bo Li, Tom Goldstein

As machine learning systems grow in scale, so do their training data requirements, forcing practitioners to automate and outsource the curation of training data in order to achieve state-of-the-art performance.

Data Poisoning

On the Limitations of Denoising Strategies as Adversarial Defenses

no code implementations17 Dec 2020 Zhonghan Niu, Zhaoxi Chen, Linyi Li, YuBin Yang, Bo Li, JinFeng Yi

Surprisingly, our experimental results show that even if most of the perturbations in each dimension is eliminated, it is still difficult to obtain satisfactory robustness.


Fair Resource Sharing with Externailities

no code implementations8 Dec 2020 Jiarui Gan, Bo Li, Yingkai Li

In particular, we are interested in a dorm assignment problem, where students are to be assigned to dorms with the same capacity and they have dichotomous preference over their dorm-mates.

Computer Science and Game Theory

UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification

1 code implementation CVPR 2021 Tianyu Zhang, Lingxi Xie, Longhui Wei, Zijie Zhuang, Yongfei Zhang, Bo Li, Qi Tian

The main difficulty of person re-identification (ReID) lies in collecting annotated data and transferring the model across different domains.

Domain Adaptation Image Generation +1

Budget-feasible Maximum Nash Social Welfare Allocation is Almost Envy-free

no code implementations7 Dec 2020 Xiaowei Wu, Bo Li, Jiarui Gan

The Nash social welfare (NSW) is a well-known social welfare measurement that balances individual utilities and the overall efficiency.

Fairness Computer Science and Game Theory Multiagent Systems

Evaluating adversarial robustness in simulated cerebellum

no code implementations5 Dec 2020 Liu Yuezhang, Bo Li, Qifeng Chen

It is well known that artificial neural networks are vulnerable to adversarial examples, in which great efforts have been made to improve the robustness.

Adversarial Robustness

Counterfactual Prediction for Bundle Treatment

no code implementations NeurIPS 2020 Hao Zou, Peng Cui, Bo Li, Zheyan Shen, Jianxin Ma, Hongxia Yang, Yue He

Estimating counterfactual outcome of different treatments from observational data is an important problem to assist decision making in a variety of fields.

Decision Making Recommendation Systems

Graph Enhanced Dual Attention Network for Document-Level Relation Extraction

no code implementations COLING 2020 Bo Li, Wei Ye, Zhonghao Sheng, Rui Xie, Xiangyu Xi, Shikun Zhang

Document-level relation extraction requires inter-sentence reasoning capabilities to capture local and global contextual information for multiple relational facts.

Document-level Relation Extraction

A Better and Faster End-to-End Model for Streaming ASR

no code implementations21 Nov 2020 Bo Li, Anmol Gulati, Jiahui Yu, Tara N. Sainath, Chung-Cheng Chiu, Arun Narayanan, Shuo-Yiin Chang, Ruoming Pang, Yanzhang He, James Qin, Wei Han, Qiao Liang, Yu Zhang, Trevor Strohman, Yonghui Wu

To address this, we explore replacing the LSTM layers in the encoder of our E2E model with Conformer layers [4], which has shown good improvements for ASR.

Audio and Speech Processing Sound

Automated Model Compression by Jointly Applied Pruning and Quantization

no code implementations12 Nov 2020 Wenting Tang, Xingxing Wei, Bo Li

In the traditional deep compression framework, iteratively performing network pruning and quantization can reduce the model size and computation cost to meet the deployment requirements.

AutoML Model Compression +3

Decoupled Appearance and Motion Learning for Efficient Anomaly Detection in Surveillance Video

no code implementations10 Nov 2020 Bo Li, Sam Leroux, Pieter Simoens

Automating the analysis of surveillance video footage is of great interest when urban environments or industrial sites are monitored by a large number of cameras.

Anomaly Detection

MUSE: Textual Attributes Guided Portrait Painting Generation

1 code implementation9 Nov 2020 Xiaodan Hu, Pengfei Yu, Kevin Knight, Heng Ji, Bo Li, Honghui Shi

Experiments show that our approach can accurately illustrate 78% textual attributes, which also help MUSE capture the subject in a more creative and expressive way.

Learning unbiased group-wise registration (LUGR) and joint segmentation: evaluation on longitudinal diffusion MRI

no code implementations3 Nov 2020 Bo Li, Wiro J. Niessen, Stefan Klein, M. Arfan Ikram, Meike W. Vernooij, Esther E. Bron

We here propose an analytical framework based on an unbiased learning strategy for group-wise registration that simultaneously registers images to the mean space of a group to obtain consistent segmentations.

NLCA-Net v2 for Stereo Matching in ECCV'20 Robust Vision Challenge

no code implementations1 Nov 2020 Zhibo Rao, Mingyi He, Bo Li, Renjie He

The network architecture used in this RVC, called as NLCA-Net v2, is consists of four parts: feature extraction, cost volume construction, feature matching, and refinement, as shown in Fig.

Stereo Matching

FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization

2 code implementations21 Oct 2020 Jiahui Yu, Chung-Cheng Chiu, Bo Li, Shuo-Yiin Chang, Tara N. Sainath, Yanzhang He, Arun Narayanan, Wei Han, Anmol Gulati, Yonghui Wu, Ruoming Pang

FastEmit also improves streaming ASR accuracy from 4. 4%/8. 9% to 3. 1%/7. 5% WER, meanwhile reduces 90th percentile latency from 210 ms to only 30 ms on LibriSpeech.

automatic-speech-recognition Speech Recognition +1

On Convergence of Nearest Neighbor Classifiers over Feature Transformations

no code implementations NeurIPS 2020 Luka Rimanic, Cedric Renggli, Bo Li, Ce Zhang

This analysis requires in-depth understanding of the properties that connect both the transformed space and the raw feature space.

Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling

no code implementations ICLR 2021 Jiahui Yu, Wei Han, Anmol Gulati, Chung-Cheng Chiu, Bo Li, Tara N. Sainath, Yonghui Wu, Ruoming Pang

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible, while full-context ASR waits for the completion of a full speech utterance before emitting completed hypotheses.

automatic-speech-recognition End-To-End Speech Recognition +2

Referring Image Segmentation via Cross-Modal Progressive Comprehension

1 code implementation CVPR 2020 Shaofei Huang, Tianrui Hui, Si Liu, Guanbin Li, Yunchao Wei, Jizhong Han, Luoqi Liu, Bo Li

In addition to the CMPC module, we further leverage a simple yet effective TGFE module to integrate the reasoned multimodal features from different levels with the guidance of textual information.

Referring Expression Segmentation Semantic Segmentation

Does Adversarial Transferability Indicate Knowledge Transferability?

no code implementations28 Sep 2020 Kaizhao Liang, Jacky Y. Zhang, Oluwasanmi O Koyejo, Bo Li

Despite the immense success that deep neural networks (DNNs) have achieved, \emph{adversarial examples}, which are perturbed inputs that aim to mislead DNNs to make mistakes, have recently led to great concerns.

Transfer Learning

CLASS: Cross-Level Attention and Supervision for Salient Objects Detection

no code implementations23 Sep 2020 Lv Tang, Bo Li

First, in order to leverage the different advantages of low-level and high-level features, we propose a novel non-local cross-level attention (CLA), which can capture the long-range feature dependencies to enhance the distinction of complete salient object.

Object Detection Salient Object Detection

Optimal Provable Robustness of Quantum Classification via Quantum Hypothesis Testing

no code implementations21 Sep 2020 Maurice Weber, Nana Liu, Bo Li, Ce Zhang, Zhikuan Zhao

This link leads to a tight robustness condition which puts constraints on the amount of noise a classifier can tolerate, independent of whether the noise source is natural or adversarial.

Classification General Classification +2

Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluation

no code implementations16 Sep 2020 Wenhao Ding, Baiming Chen, Bo Li, Kim Ji Eun, Ding Zhao

Existing neural network-based autonomous systems are shown to be vulnerable against adversarial attacks, therefore sophisticated evaluation on their robustness is of great importance.

Decision Making

SoK: Certified Robustness for Deep Neural Networks

2 code implementations9 Sep 2020 Linyi Li, Xiangyu Qi, Tao Xie, Bo Li

Great advancement in deep neural networks (DNNs) has led to state-of-the-art performance on a wide range of tasks.

Autonomous Driving

ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation

no code implementations7 Sep 2020 Sicheng Zhao, Yezhen Wang, Bo Li, Bichen Wu, Yang Gao, Pengfei Xu, Trevor Darrell, Kurt Keutzer

They require prior knowledge of real-world statistics and ignore the pixel-level dropout noise gap and the spatial feature gap between different domains.

Autonomous Driving Domain Adaptation +2

A Review of Single-Source Deep Unsupervised Visual Domain Adaptation

1 code implementation1 Sep 2020 Sicheng Zhao, Xiangyu Yue, Shanghang Zhang, Bo Li, Han Zhao, Bichen Wu, Ravi Krishna, Joseph E. Gonzalez, Alberto L. Sangiovanni-Vincentelli, Sanjit A. Seshia, Kurt Keutzer

To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain.

Unsupervised Domain Adaptation

Scalable Multiple Changepoint Detection for Functional Data Sequences

no code implementations5 Aug 2020 Trevor Harris, Bo Li, James Derek Tucker

We show that our method outperforms a recent multiple functional changepoint detector and several univariate changepoint detectors applied to our proposed projections.

Denoising Time Series Methodology

Relative Pose Estimation of Calibrated Cameras with Known $\mathrm{SE}(3)$ Invariants

no code implementations15 Jul 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

On uncertainty estimation in active learning for image segmentation

1 code implementation13 Jul 2020 Bo Li, Tommy Sonne Alstrøm

This is especially critical in the data-driven active learning setting where the goal is to achieve a certain accuracy with minimum labeling effort.

Active Learning Medical Image Segmentation

Adversarial Mutual Information for Text Generation

1 code implementation ICML 2020 Boyuan Pan, Yazheng Yang, Kaizhao Liang, Bhavya Kailkhura, Zhongming Jin, Xian-Sheng Hua, Deng Cai, Bo Li

Recent advances in maximizing mutual information (MI) between the source and target have demonstrated its effectiveness in text generation.

Text Generation

Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability

2 code implementations25 Jun 2020 Kaizhao Liang, Jacky Y. Zhang, Boxin Wang, Zhuolin Yang, Oluwasanmi Koyejo, Bo Li

Knowledge transferability, or transfer learning, has been widely adopted to allow a pre-trained model in the source domain to be effectively adapted to downstream tasks in the target domain.

Transfer Learning

Global Convergence and Generalization Bound of Gradient-Based Meta-Learning with Deep Neural Nets

2 code implementations25 Jun 2020 Haoxiang Wang, Ruoyu Sun, Bo Li

Gradient-based meta-learning (GBML) with deep neural nets (DNNs) has become a popular approach for few-shot learning.

Few-Shot Learning

Rethinking Distributional Matching Based Domain Adaptation

no code implementations23 Jun 2020 Bo Li, Yezhen Wang, Tong Che, Shanghang Zhang, Sicheng Zhao, Pengfei Xu, Wei Zhou, Yoshua Bengio, Kurt Keutzer

In this paper, in order to devise robust DA algorithms, we first systematically analyze the limitations of DM based methods, and then build new benchmarks with more realistic domain shifts to evaluate the well-accepted DM methods.

Domain Adaptation

Algorithmic Decision Making with Conditional Fairness

1 code implementation18 Jun 2020 Renzhe Xu, Peng Cui, Kun Kuang, Bo Li, Linjun Zhou, Zheyan Shen, Wei Cui

In practice, there frequently exist a certain set of variables we term as fair variables, which are pre-decision covariates such as users' choices.

Decision Making Fairness

Learning Decomposed Representation for Counterfactual Inference

no code implementations12 Jun 2020 Anpeng Wu, Kun Kuang, Junkun Yuan, Bo Li, Runze Wu, Qiang Zhu, Yueting Zhuang, Fei Wu

The fundamental problem in treatment effect estimation from observational data is confounder identification and balancing.

Counterfactual Inference

Weighted Lasso Estimates for Sparse Logistic Regression: Non-asymptotic Properties with Measurement Error

no code implementations11 Jun 2020 Huamei Huang, Yujing Gao, Huiming Zhang, Bo Li

When we are interested in high-dimensional system and focus on classification performance, the $\ell_{1}$-penalized logistic regression is becoming important and popular.

Stable Prediction via Leveraging Seed Variable

no code implementations9 Jun 2020 Kun Kuang, Bo Li, Peng Cui, Yue Liu, Jianrong Tao, Yueting Zhuang, Fei Wu

By assuming the relationships between causal variables and response variable are invariant across data, to address this problem, we propose a conditional independence test based algorithm to separate those causal variables with a seed variable as priori, and adopt them for stable prediction.

Stable Adversarial Learning under Distributional Shifts

no code implementations8 Jun 2020 Jiashuo Liu, Zheyan Shen, Peng Cui, Linjun Zhou, Kun Kuang, Bo Li, Yishi Lin

Machine learning algorithms with empirical risk minimization are vulnerable under distributional shifts due to the greedy adoption of all the correlations found in training data.

Recapture as You Want

no code implementations2 Jun 2020 Chen Gao, Si Liu, Ran He, Shuicheng Yan, Bo Li

LGR module utilizes body skeleton knowledge to construct a layout graph that connects all relevant part features, where graph reasoning mechanism is used to propagate information among part nodes to mine their relations.

QEBA: Query-Efficient Boundary-Based Blackbox Attack

no code implementations CVPR 2020 Huichen Li, Xiaojun Xu, Xiaolu Zhang, Shuang Yang, Bo Li

Such adversarial attacks can be achieved by adding a small magnitude of perturbation to the input to mislead model prediction.

Autonomous Driving Dimensionality Reduction

A Quantitative Survey of Communication Optimizations in Distributed Deep Learning

1 code implementation27 May 2020 Shaohuai Shi, Zhenheng Tang, Xiaowen Chu, Chengjian Liu, Wei Wang, Bo Li

In this article, we present a quantitative survey of communication optimization techniques for data parallel distributed DL.

Improved Noisy Student Training for Automatic Speech Recognition

no code implementations19 May 2020 Daniel S. Park, Yu Zhang, Ye Jia, Wei Han, Chung-Cheng Chiu, Bo Li, Yonghui Wu, Quoc V. Le

Noisy student training is an iterative self-training method that leverages augmentation to improve network performance.

Ranked #4 on Speech Recognition on LibriSpeech test-clean (using extra training data)

automatic-speech-recognition Image Classification +1

DBA: Distributed Backdoor Attacks against Federated Learning

2 code implementations ICLR 2020 Chulin Xie, Keli Huang, Pin-Yu Chen, Bo Li

Compared to standard centralized backdoors, we show that DBA is substantially more persistent and stealthy against FL on diverse datasets such as finance and image data.

Feature Importance Federated Learning

Towards Fast and Accurate Streaming End-to-End ASR

no code implementations24 Apr 2020 Bo Li, Shuo-Yiin Chang, Tara N. Sainath, Ruoming Pang, Yanzhang He, Trevor Strohman, Yonghui Wu

RNN-T EP+LAS, together with MWER training brings in 18. 7% relative WER reduction and 160ms 90-percentile latency reductions compared to the original proposed RNN-T EP model.

Audio and Speech Processing

GAPS: Generator for Automatic Polynomial Solvers

1 code implementation24 Apr 2020 Bo Li, Viktor Larsson

Minimal problems in computer vision raise the demand of generating efficient automatic solvers for polynomial equation systems.

Space of Functions Computed by Deep-Layered Machines

no code implementations19 Apr 2020 Alexander Mozeika, Bo Li, David Saad

We study the space of functions computed by random-layered machines, including deep neural networks and Boolean circuits.

Towards Evaluating the Robustness of Chinese BERT Classifiers

no code implementations7 Apr 2020 Boxin Wang, Boyuan Pan, Xin Li, Bo Li

Recent advances in large-scale language representation models such as BERT have improved the state-of-the-art performances in many NLP tasks.

Controllable Orthogonalization in Training DNNs

1 code implementation CVPR 2020 Lei Huang, Li Liu, Fan Zhu, Diwen Wan, Zehuan Yuan, Bo Li, Ling Shao

Orthogonality is widely used for training deep neural networks (DNNs) due to its ability to maintain all singular values of the Jacobian close to 1 and reduce redundancy in representation.

Image Classification

A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency

no code implementations28 Mar 2020 Tara N. Sainath, Yanzhang He, Bo Li, Arun Narayanan, Ruoming Pang, Antoine Bruguier, Shuo-Yiin Chang, Wei Li, Raziel Alvarez, Zhifeng Chen, Chung-Cheng Chiu, David Garcia, Alex Gruenstein, Ke Hu, Minho Jin, Anjuli Kannan, Qiao Liang, Ian McGraw, Cal Peyser, Rohit Prabhavalkar, Golan Pundak, David Rybach, Yuan Shangguan, Yash Sheth, Trevor Strohman, Mirko Visontai, Yonghui Wu, Yu Zhang, Ding Zhao

Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art conventional models with respect to both quality, i. e., word error rate (WER), and latency, i. e., the time the hypothesis is finalized after the user stops speaking.

Multi-Task Learning Enhanced Single Image De-Raining

1 code implementation21 Mar 2020 Yulong Fan, Rong Chen, Bo Li

Rain removal in images is an important task in computer vision filed and attracting attentions of more and more people.

Multi-Task Learning Rain Removal

Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations

3 code implementations NeurIPS 2020 Huan Zhang, Hongge Chen, Chaowei Xiao, Bo Li, Mingyan Liu, Duane Boning, Cho-Jui Hsieh

Several works have shown this vulnerability via adversarial attacks, but existing approaches on improving the robustness of DRL under this setting have limited success and lack for theoretical principles.

RAB: Provable Robustness Against Backdoor Attacks

1 code implementation19 Mar 2020 Maurice Weber, Xiaojun Xu, Bojan Karlaš, Ce Zhang, Bo Li

We then propose the first robust training process, RAB, to smooth the trained model and certify its robustness against backdoor attacks.

Anomalous Example Detection in Deep Learning: A Survey

no code implementations16 Mar 2020 Saikiran Bulusu, Bhavya Kailkhura, Bo Li, Pramod K. Varshney, Dawn Song

This survey tries to provide a structured and comprehensive overview of the research on anomaly detection for DL based applications.

Anomaly Detection

Communication-Efficient Distributed Deep Learning: A Comprehensive Survey

no code implementations10 Mar 2020 Zhenheng Tang, Shaohuai Shi, Xiaowen Chu, Wei Wang, Bo Li

Distributed deep learning becomes very common to reduce the overall training time by exploiting multiple computing devices (e. g., GPUs/TPUs) as the size of deep models and data sets increases.

Controllable Time-Delay Transformer for Real-Time Punctuation Prediction and Disfluency Detection

no code implementations3 Mar 2020 Qian Chen, Mengzhe Chen, Bo Li, Wen Wang

With the increased applications of automatic speech recognition (ASR) in recent years, it is essential to automatically insert punctuation marks and remove disfluencies in transcripts, to improve the readability of the transcripts as well as the performance of subsequent applications, such as machine translation, dialogue systems, and so forth.

automatic-speech-recognition Machine Translation +2

End-to-end Robustness for Sensing-Reasoning Machine Learning Pipelines

no code implementations28 Feb 2020 Zhuolin Yang, Zhikuan Zhao, Hengzhi Pei, Boxin Wang, Bojan Karlas, Ji Liu, Heng Guo, Bo Li, Ce Zhang

We show that for reasoning components such as MLN and a specific family of Bayesian networks it is possible to certify the robustness of the whole pipeline even with a large magnitude of perturbation which cannot be certified by existing work.

TSS: Transformation-Specific Smoothing for Robustness Certification

1 code implementation27 Feb 2020 Linyi Li, Maurice Weber, Xiaojun Xu, Luka Rimanic, Bhavya Kailkhura, Tao Xie, Ce Zhang, Bo Li

Moreover, to the best of our knowledge, TSS is the first approach that achieves nontrivial certified robustness on the large-scale ImageNet dataset.

Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey

no code implementations26 Feb 2020 Sicheng Zhao, Bo Li, Colorado Reed, Pengfei Xu, Kurt Keutzer

Therefore, transferring the learned knowledge from a separate, labeled source domain to an unlabeled or sparsely labeled target domain becomes an appealing alternative.

Domain Adaptation

Improving Robustness of Deep-Learning-Based Image Reconstruction

no code implementations ICML 2020 Ankit Raj, Yoram Bresler, Bo Li

We find that a linear network using the proposed min-max learning scheme indeed converges to the same solution.

Image Reconstruction

Identification and Validation of the SNV Biomarkers Based on Multi-Dimensional Patterns

no code implementations25 Feb 2020 Bo Li, Junying Zhang, Liang Yu

It is feasible to classify the cancer of the sample by the distribution of different dimensions of the SNVs and has a high accuracy.

MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation

1 code implementation19 Feb 2020 Sicheng Zhao, Bo Li, Xiangyu Yue, Pengfei Xu, Kurt Keutzer

Finally, feature-level alignment is performed between the aggregated domain and the target domain while training the task network.

Domain Adaptation Object Classification +1

Reinforcement-Learning based Portfolio Management with Augmented Asset Movement Prediction States

1 code implementation9 Feb 2020 Yunan Ye, Hengzhi Pei, Boxin Wang, Pin-Yu Chen, Yada Zhu, Jun Xiao, Bo Li

Our framework aims to address two unique challenges in financial PM: (1) data heterogeneity -- the collected information for each asset is usually diverse, noisy and imbalanced (e. g., news articles); and (2) environment uncertainty -- the financial market is versatile and non-stationary.

AI-GAN: Attack-Inspired Generation of Adversarial Examples

1 code implementation6 Feb 2020 Tao Bai, Jun Zhao, Jinlin Zhu, Shoudong Han, Jiefeng Chen, Bo Li, Alex Kot

Deep neural networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding imperceptible perturbations to inputs.

Stable Prediction with Model Misspecification and Agnostic Distribution Shift

no code implementations31 Jan 2020 Kun Kuang, Ruoxuan Xiong, Peng Cui, Susan Athey, Bo Li

Then, these weights are used in the weighted regression to improve the accuracy of estimation on the effect of each variable, thus help to improve the stability of prediction across unknown test data.

Efficient Probabilistic Logic Reasoning with Graph Neural Networks

1 code implementation ICLR 2020 Yuyu Zhang, Xinshi Chen, Yuan Yang, Arun Ramamurthy, Bo Li, Yuan Qi, Le Song

In this paper, we explore the combination of MLNs and GNNs, and use graph neural networks for variational inference in MLN.

Variational Inference

Sparse Black-box Video Attack with Reinforcement Learning

no code implementations11 Jan 2020 Huanqian Yan, Xingxing Wei, Bo Li

Specifically, the environment in RL is set as the threat model, and the agent in RL plays the role of frame selecting.

Video Recognition

Attack-Resistant Federated Learning with Residual-based Reweighting

2 code implementations24 Dec 2019 Shuhao Fu, Chulin Xie, Bo Li, Qifeng Chen

Federated learning has a variety of applications in multiple domains by utilizing private training data stored on different devices.

Federated Learning

T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack

3 code implementations EMNLP 2020 Boxin Wang, Hengzhi Pei, Boyuan Pan, Qian Chen, Shuohang Wang, Bo Li

In particular, we propose a tree-based autoencoder to embed the discrete text data into a continuous representation space, upon which we optimize the adversarial perturbation.

Adversarial Attack Adversarial Text +3

Learning to Prevent Leakage: Privacy-Preserving Inference in the Mobile Cloud

no code implementations18 Dec 2019 Shuang Zhang, Liyao Xiang, CongCong Li, YiXuan Wang, Quanshi Zhang, Wei Wang, Bo Li

Powered by machine learning services in the cloud, numerous learning-driven mobile applications are gaining popularity in the market.

Neural Architecture Search Privacy Preserving Deep Learning

MG-WFBP: Merging Gradients Wisely for Efficient Communication in Distributed Deep Learning

1 code implementation18 Dec 2019 Shaohuai Shi, Xiaowen Chu, Bo Li

Distributed synchronous stochastic gradient descent has been widely used to train deep neural networks (DNNs) on computer clusters.

SpecAugment on Large Scale Datasets

no code implementations11 Dec 2019 Daniel S. Park, Yu Zhang, Chung-Cheng Chiu, Youzheng Chen, Bo Li, William Chan, Quoc V. Le, Yonghui Wu

Recently, SpecAugment, an augmentation scheme for automatic speech recognition that acts directly on the spectrogram of input utterances, has shown to be highly effective in enhancing the performance of end-to-end networks on public datasets.

automatic-speech-recognition Speech Recognition

Naive Gabor Networks for Hyperspectral Image Classification

no code implementations9 Dec 2019 Chenying Liu, Jun Li, Lin He, Antonio J. Plaza, Shutao Li, Bo Li

Specifically, we develop an innovative phase-induced Gabor kernel, which is trickily designed to perform the Gabor feature learning via a linear combination of local low-frequency and high-frequency components of data controlled by the kernel phase.

Classification General Classification +1

A SVBRDF Modeling Pipeline using Pixel Clustering

1 code implementation1 Dec 2019 Bo Li, Jie Feng, Bingfeng Zhou

We present a pipeline for modeling spatially varying BRDFs (svBRDFs) of planar materials which only requires a mobile phone for data acquisition.


Facility Location Problem with Capacity Constraints: Algorithmic and Mechanism Design Perspectives

no code implementations22 Nov 2019 Haris Aziz, Hau Chan, Barton E. Lee, Bo Li, Toby Walsh

From the algorithmic perspective, we prove that the corresponding optimization problem, where the goal is to locate facilities to minimize either the total cost to all agents or the maximum cost of any agent is NP-hard.

Rule-Guided Compositional Representation Learning on Knowledge Graphs

1 code implementation20 Nov 2019 Guanglin Niu, Yongfei Zhang, Bo Li, Peng Cui, Si Liu, Jingyang Li, Xiaowei Zhang

Representation learning on a knowledge graph (KG) is to embed entities and relations of a KG into low-dimensional continuous vector spaces.

Knowledge Graphs Representation Learning

REFIT: A Unified Watermark Removal Framework For Deep Learning Systems With Limited Data

1 code implementation17 Nov 2019 Xinyun Chen, Wenxiao Wang, Chris Bender, Yiming Ding, Ruoxi Jia, Bo Li, Dawn Song

The experimental results demonstrate that our fine-tuning based watermark removal attacks could pose real threats to the copyright of pre-trained models, and thus highlight the importance of further investigating the watermarking problem and proposing more robust watermark embedding schemes against the attacks.


Scalability vs. Utility: Do We Have to Sacrifice One for the Other in Data Importance Quantification?

no code implementations CVPR 2021 Ruoxi Jia, Fan Wu, Xuehui Sun, Jiacen Xu, David Dao, Bhavya Kailkhura, Ce Zhang, Bo Li, Dawn Song

Quantifying the importance of each training point to a learning task is a fundamental problem in machine learning and the estimated importance scores have been leveraged to guide a range of data workflows such as data summarization and domain adaption.

Data Summarization Domain Adaptation

The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks

no code implementations CVPR 2020 Yuheng Zhang, Ruoxi Jia, Hengzhi Pei, Wenxiao Wang, Bo Li, Dawn Song

This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data.

Face Recognition

ChebNet: Efficient and Stable Constructions of Deep Neural Networks with Rectified Power Units using Chebyshev Approximations

2 code implementations7 Nov 2019 Shanshan Tang, Bo Li, Haijun Yu

In this paper, we propose a new and more stable way to construct deep RePU neural networks based on Chebyshev polynomial approximations.

Hierarchical structure

Large Deviation Analysis of Function Sensitivity in Random Deep Neural Networks

no code implementations13 Oct 2019 Bo Li, David Saad

Mean field theory has been successfully used to analyze deep neural networks (DNN) in the infinite size limit.


DeGNN: Characterizing and Improving Graph Neural Networks with Graph Decomposition

no code implementations10 Oct 2019 Xupeng Miao, Nezihe Merve Gürel, Wentao Zhang, Zhichao Han, Bo Li, Wei Min, Xi Rao, Hansheng Ren, Yinan Shan, Yingxia Shao, Yujie Wang, Fan Wu, Hui Xue, Yaming Yang, Zitao Zhang, Yang Zhao, Shuai Zhang, Yujing Wang, Bin Cui, Ce Zhang

Despite the wide application of Graph Convolutional Network (GCN), one major limitation is that it does not benefit from the increasing depth and suffers from the oversmoothing problem.

Detecting AI Trojans Using Meta Neural Analysis

1 code implementation8 Oct 2019 Xiaojun Xu, Qi. Wang, Huichen Li, Nikita Borisov, Carl A. Gunter, Bo Li

To train the meta-model without knowledge of the attack strategy, we introduce a technique called jumbo learning that samples a set of Trojaned models following a general distribution.

Data Poisoning

Neural Zero-Inflated Quality Estimation Model For Automatic Speech Recognition System

no code implementations3 Oct 2019 Kai Fan, Jiayi Wang, Bo Li, Shiliang Zhang, Boxing Chen, Niyu Ge, Zhijie Yan

The performances of automatic speech recognition (ASR) systems are usually evaluated by the metric word error rate (WER) when the manually transcribed data are provided, which are, however, expensively available in the real scenario.

automatic-speech-recognition Language Modelling +3