Search Results for author: Li Li

Found 176 papers, 50 papers with code

Modeling Hierarchical Syntax Structure with Triplet Position for Source Code Summarization

no code implementations ACL 2022 Juncai Guo, Jin Liu, Yao Wan, Li Li, Pingyi Zhou

In this paper, we propose CODESCRIBE to model the hierarchical syntax structure of code by introducing a novel triplet position for code summarization.

Code Summarization Position +1

Breaking the Memory Wall for Heterogeneous Federated Learning with Progressive Training

no code implementations20 Apr 2024 Yebo Wu, Li Li, Chunlin Tian, Chengzhong Xu

In order to preserve the feature representation of each block, we decouple the whole training process into two stages: progressive model shrinking and progressive model growing.

Open-Source AI-based SE Tools: Opportunities and Challenges of Collaborative Software Learning

no code implementations9 Apr 2024 ZhiHao Lin, Wei Ma, Tao Lin, Yaowen Zheng, Jingquan Ge, Jun Wang, Jacques Klein, Tegawende Bissyande, Yang Liu, Li Li

We introduce a governance framework centered on federated learning (FL), designed to foster the joint development and maintenance of open-source AI code models while safeguarding data privacy and security.

Federated Learning

Motion-aware 3D Gaussian Splatting for Efficient Dynamic Scene Reconstruction

no code implementations18 Mar 2024 Zhiyang Guo, Wengang Zhou, Li Li, Min Wang, Houqiang Li

To address the above problem, we propose a novel motion-aware enhancement framework for dynamic scene reconstruction, which mines useful motion cues from optical flow to improve different paradigms of dynamic 3DGS.

Optical Flow Estimation

Object Segmentation-Assisted Inter Prediction for Versatile Video Coding

no code implementations18 Mar 2024 Zhuoyuan Li, Zikun Yuan, Li Li, Dong Liu, Xiaohu Tang, Feng Wu

Moreover, segmentation mask is considered in the joint rate-distortion optimization for motion estimation and partition estimation to derive the motion vector of different regions and partition more accurately.

Motion Compensation Motion Estimation +3

Towards Personalized Evaluation of Large Language Models with An Anonymous Crowd-Sourcing Platform

no code implementations13 Mar 2024 Mingyue Cheng, Hao Zhang, Jiqian Yang, Qi Liu, Li Li, Xin Huang, Liwei Song, Zhi Li, Zhenya Huang, Enhong Chen

Through this gateway, users have the opportunity to submit their questions, testing the models on a personalized and potentially broader range of capabilities.

Language Modelling Large Language Model

DLP-GAN: learning to draw modern Chinese landscape photos with generative adversarial network

no code implementations6 Mar 2024 Xiangquan Gui, Binxuan Zhang, Li Li, Yi Yang

To solve such problems, in this paper, we (1) propose DLP-GAN (Draw Modern Chinese Landscape Photos with Generative Adversarial Network), an unsupervised cross-domain image translation framework with a novel asymmetric cycle mapping, and (2) introduce a generator based on a dense-fusion module to match different translation directions.

Generative Adversarial Network Translation

LoRA-as-an-Attack! Piercing LLM Safety Under The Share-and-Play Scenario

no code implementations29 Feb 2024 Hongyi Liu, Zirui Liu, Ruixiang Tang, Jiayi Yuan, Shaochen Zhong, Yu-Neng Chuang, Li Li, Rui Chen, Xia Hu

Our aim is to raise awareness of the potential risks under the emerging share-and-play scenario, so as to proactively prevent potential consequences caused by LoRA-as-an-Attack.

Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigation

no code implementations25 Feb 2024 Xiaohan Lei, Min Wang, Wengang Zhou, Li Li, Houqiang Li

As a new embodied vision task, Instance ImageGoal Navigation (IIN) aims to navigate to a specified object depicted by a goal image in an unexplored environment.


Investigating White-Box Attacks for On-Device Models

1 code implementation8 Feb 2024 Mingyi Zhou, Xiang Gao, Jing Wu, Kui Liu, Hailong Sun, Li Li

Our findings emphasize the need for developers to carefully consider their model deployment strategies, and use white-box methods to evaluate the vulnerability of on-device models.

Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compression

no code implementations29 Jan 2024 Xihua Sheng, Li Li, Dong Liu, Houqiang Li

With the SDD-based motion model and long short-term temporal contexts fusion, our proposed learned video codec can obtain more accurate inter prediction.

Motion Estimation MS-SSIM +2

PL-FSCIL: Harnessing the Power of Prompts for Few-Shot Class-Incremental Learning

no code implementations26 Jan 2024 Songsong Tian, Lusi Li, Weijun Li, Hang Ran, Li Li, Xin Ning

In this paper, we propose a novel approach called Prompt Learning for FSCIL (PL-FSCIL), which harnesses the power of prompts in conjunction with a pre-trained Vision Transformer (ViT) model to address the challenges of FSCIL effectively.

Few-Shot Class-Incremental Learning Incremental Learning

Shift-ConvNets: Small Convolutional Kernel with Large Kernel Effects

1 code implementation23 Jan 2024 Dachong Li, Li Li, Zhuangzhuang Chen, Jianqiang Li

Experimental results show that our shift-wise operator significantly improves the accuracy of a regular CNN while markedly reducing computational requirements.

When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference

1 code implementation18 Jan 2024 Zhensu Sun, Xiaoning Du, Fu Song, Shangwen Wang, Li Li

These findings motivate our exploration of dynamic inference in code completion and inspire us to enhance it with a decision-making mechanism that stops the generation of incorrect code.

Code Completion Decision Making

Multi-objective Optimal Roadside Units Deployment in Urban Vehicular Networks

no code implementations14 Jan 2024 Weian Guo, Zecheng Kang, Dongyang Li, Lun Zhang, Li Li

Therefore, the deployment of RSUs is of utmost importance in ensuring the quality of communication services.

DarkShot: Lighting Dark Images with Low-Compute and High-Quality

no code implementations28 Dec 2023 Jiazhang Zheng, Lei LI, Qiuping Liao, Cheng Li, Li Li, Yangxing Liu

This paper proposes a lightweight network that outperforms existing state-of-the-art (SOTA) methods in low-light enhancement tasks while minimizing computation.

4k Image Restoration

How to Configure Good In-Context Sequence for Visual Question Answering

1 code implementation4 Dec 2023 Li Li, Jiawei Peng, Huiyi Chen, Chongyang Gao, Xu Yang

Inspired by the success of Large Language Models in dealing with new tasks via In-Context Learning (ICL) in NLP, researchers have also developed Large Vision-Language Models (LVLMs) with ICL capabilities.

In-Context Learning Question Answering +2

Progressive Recurrent Network for Shadow Removal

no code implementations1 Nov 2023 Yonghui Wang, Wengang Zhou, Hao Feng, Li Li, Houqiang Li

To handle this issue, we consider removing the shadow in a coarse-to-fine fashion and propose a simple but effective Progressive Recurrent Network (PRNet).

Image Shadow Removal Shadow Removal

Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey

1 code implementation27 Oct 2023 Xinyu She, Yue Liu, Yanjie Zhao, Yiling He, Li Li, Chakkrit Tantithamthavorn, Zhan Qin, Haoyu Wang

After carefully examining these studies, we designed a taxonomy of pitfalls in LM4Code research and conducted a systematic study to summarize the issues, implications, current solutions, and challenges of different pitfalls for LM4Code systems.

Code Generation

Domain-wise Invariant Learning for Panoptic Scene Graph Generation

no code implementations9 Oct 2023 Li Li, You Qin, Wei Ji, Yuxiao Zhou, Roger Zimmermann

Panoptic Scene Graph Generation (PSG) involves the detection of objects and the prediction of their corresponding relationships (predicates).

Graph Generation Panoptic Scene Graph Generation

Towards Complex-query Referring Image Segmentation: A Novel Benchmark

no code implementations29 Sep 2023 Wei Ji, Li Li, Hao Fei, Xiangyan Liu, Xun Yang, Juncheng Li, Roger Zimmermann

Referring Image Understanding (RIS) has been extensively studied over the past decade, leading to the development of advanced algorithms.

Image Segmentation Semantic Segmentation

On Uniform Scalar Quantization for Learned Image Compression

no code implementations29 Sep 2023 Haotian Zhang, Li Li, Dong Liu

In principle, we find two factors crucial: one is the discrepancy between the surrogate and rounding, leading to train-test mismatch; the other is gradient estimation risk due to the surrogate, which consists of bias and variance of the gradient estimation.

Image Compression Quantization

Forecasting large collections of time series: feature-based methods

1 code implementation25 Sep 2023 Li Li, Feng Li, Yanfei Kang

In economics and many other forecasting domains, the real world problems are too complex for a single model that assumes a specific data generation process.

Model Selection Time Series

Pop Quiz! Do Pre-trained Code Models Possess Knowledge of Correct API Names?

no code implementations14 Sep 2023 Terry Yue Zhuo, Xiaoning Du, Zhenchang Xing, Jiamou Sun, Haowei Quan, Li Li, Liming Zhu

The correctness and unambiguity of API usage among these code models are crucial for achieving desirable program functionalities, requiring them to learn various API fully qualified names structurally and semantically.

Code Generation Knowledge Probing

CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models

1 code implementation28 Aug 2023 Zhensu Sun, Xiaoning Du, Fu Song, Li Li

Even worse, the ``black-box'' nature of neural models sets a high barrier for externals to audit their training datasets, which further connives these unauthorized usages.

Code Completion Specificity

Learning Cyber Defence Tactics from Scratch with Multi-Agent Reinforcement Learning

no code implementations25 Aug 2023 Jacob Wiebe, Ranwa Al Mallah, Li Li

Recent advancements in deep learning techniques have opened new possibilities for designing solutions for autonomous cyber defence.

Multi-agent Reinforcement Learning reinforcement-learning

Large Language Models for Software Engineering: A Systematic Literature Review

1 code implementation21 Aug 2023 Xinyi Hou, Yanjie Zhao, Yue Liu, Zhou Yang, Kailong Wang, Li Li, Xiapu Luo, David Lo, John Grundy, Haoyu Wang

Nevertheless, a comprehensive understanding of the application, effects, and possible limitations of LLMs on SE is still in its early stages.

Causal SAR ATR with Limited Data via Dual Invariance

1 code implementation18 Aug 2023 Chenwei Wang, You Qin, Li Li, Siyi Luo, Yulin Huang, Jifang Pei, Yin Zhang, Jianyu Yang

As a result, it has a detrimental causal effect damaging the efficacy of feature $X$ extracted from SAR images, leading to weak generalization of SAR ATR with limited data.

SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning

no code implementations ICCV 2023 Hao Feng, Wendi Wang, Jiajun Deng, Wengang Zhou, Li Li, Houqiang Li

To make the best of such rectification cues, we introduce SimFIR, a simple framework for fisheye image rectification based on self-supervised representation learning.

Representation Learning

Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection

1 code implementation ICCV 2023 Yufei Yin, Jiajun Deng, Wengang Zhou, Li Li, Houqiang Li

These inaccurate high-scoring region proposals will mislead the training of subsequent refinement modules and thus hamper the detection performance.

Object object-detection +1

Deep Semantic Graph Matching for Large-scale Outdoor Point Clouds Registration

no code implementations10 Aug 2023 Shaocong Liu, Tao Wang, Yan Zhang, Ruqin Zhou, Li Li, Chenguang Dai, Yongsheng Zhang, Longguang Wang, Hanyun Wang

The adjacent points with the same category labels are then clustered together using the Euclidean clustering algorithm to obtain the semantic instances, which are represented by three kinds of attributes including spatial location information, semantic categorical information, and global geometric shape information.

Graph Matching Point Cloud Registration +1

Exploiting Spatial-Temporal Context for Interacting Hand Reconstruction on Monocular RGB Video

no code implementations8 Aug 2023 Weichao Zhao, Hezhen Hu, Wengang Zhou, Li Li, Houqiang Li

Reconstructing interacting hands from monocular RGB data is a challenging task, as it involves many interfering factors, e. g. self- and mutual occlusion and similar textures.

Efficient Temporal Sentence Grounding in Videos with Multi-Teacher Knowledge Distillation

no code implementations7 Aug 2023 Renjie Liang, Yiming Yang, Hui Lu, Li Li

To tackle this problem, we propose a novel efficient multi-teacher model (EMTM) based on knowledge distillation to transfer diverse knowledge from both heterogeneous and isomorphic networks.

Knowledge Distillation Sentence +1

Panoptic Scene Graph Generation with Semantics-Prototype Learning

1 code implementation28 Jul 2023 Li Li, Wei Ji, Yiming Wu, Mengze Li, You Qin, Lina Wei, Roger Zimmermann

To promise consistency and accuracy during the transfer process, we propose to measure the invariance of representations in each predicate class, and learn unbiased prototypes of predicates with different intensities.

Graph Generation Panoptic Scene Graph Generation

HTP: Exploiting Holistic Temporal Patterns for Sequential Recommendation

1 code implementation22 Jul 2023 Chen Rui, Liang Guotao, Ma Chenrui, Han Qilong, Li Li, Huang Xiao

In this paper, we systematically investigate various temporal information for sequential recommendation and identify three types of advantageous temporal patterns beyond order, including absolute time information, relative item time intervals and relative recommendation time intervals.

Sequential Recommendation

IR Design for Application-Specific Natural Language: A Case Study on Traffic Data

no code implementations13 Jul 2023 Wei Hu, Xuhong Wang, Ding Wang, Shengyue Yao, Zuqiu Mao, Li Li, Fei-Yue Wang, Yilun Lin

In the realm of software applications in the transportation industry, Domain-Specific Languages (DSLs) have enjoyed widespread adoption due to their ease of use and various other benefits.

Offline and Online Optical Flow Enhancement for Deep Video Compression

no code implementations11 Jul 2023 Chuanbo Tang, Xihua Sheng, Zhuoyuan Li, Haotian Zhang, Li Li, Dong Liu

In the offline stage, we fine-tune a trained optical flow estimation network with the motion information provided by a traditional (non-deep) video compression scheme, e. g. H. 266/VVC, as we believe the motion information of H. 266/VVC achieves a better rate-distortion trade-off.

Motion Estimation Optical Flow Estimation +1

VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision

no code implementations19 Jun 2023 Xihua Sheng, Li Li, Dong Liu, Houqiang Li

Such compact representations need to be decoded back to pixels before being displayed to humans and - as usual - before being enhanced/analyzed by machine vision algorithms.

Motion Compensation Motion Estimation +2

Breaking On-device Training Memory Wall: A Systematic Survey

no code implementations17 Jun 2023 Shitian Li, Chunlin Tian, Kahou Tam, Rui Ma, Li Li

In this systematic survey, we aim to explore the current state-of-the-art techniques for breaking on-device training memory walls, focusing on methods that can enable larger and more complex models to be trained on resource-constrained devices.


Source Code Data Augmentation for Deep Learning: A Survey

1 code implementation31 May 2023 Terry Yue Zhuo, Zhou Yang, Zhensu Sun, YuFei Wang, Li Li, Xiaoning Du, Zhenchang Xing, David Lo

This paper fills this gap by conducting a comprehensive and integrative survey of data augmentation for source code, wherein we systematically compile and encapsulate existing literature to provide a comprehensive overview of the field.

Data Augmentation

Continuous and Noninvasive Measurement of Arterial Pulse Pressure and Pressure Waveform using an Image-free Ultrasound System

no code implementations29 May 2023 Lirui Xu, Pang Wu, Pan Xia, Fanglin Geng, Peng Wang, Xianxiang Chen, Zhenfeng Li, Lidong Du, Shuping Liu, Li Li, Hongbo Chang, Zhen Fang

In in vitro cardiovascular phantom experiments, the results demonstrated high accuracy in the measurement of PP (error < 3 mmHg) and blood pressure waveform (root-mean-square-errors (RMSE) < 2 mmHg, correlation coefficient (r) > textgreater 0. 99).

An Efficient Safety-oriented Car-following Model for Connected Automated Vehicles Considering Discrete Signals

no code implementations29 May 2023 DianChao Lin, Li Li

This paper proposes an efficient safety-oriented car-following model for CAVs considering the impact of discrete signals.

Decision Making

AdaptGear: Accelerating GNN Training via Adaptive Subgraph-Level Kernels on GPUs

no code implementations27 May 2023 Yangjie Zhou, Yaoxu Song, Jingwen Leng, Zihan Liu, Weihao Cui, Zhendong Zhang, Cong Guo, Quan Chen, Li Li, Minyi Guo

Graph neural networks (GNNs) are powerful tools for exploring and learning from graph structures and features.

TransWorldNG: Traffic Simulation via Foundation Model

1 code implementation25 May 2023 Ding Wang, Xuhong Wang, Liang Chen, Shengyue Yao, Ming Jing, Honghai Li, Li Li, Shiqiang Bao, Fei-Yue Wang, Yilun Lin

To the best of our knowledge, this is the first traffic simulator that can automatically learn traffic patterns from real-world data and efficiently generate accurate and realistic traffic environments.

Decision Making Management

Editable Graph Neural Network for Node Classifications

no code implementations24 May 2023 Zirui Liu, Zhimeng Jiang, Shaochen Zhong, Kaixiong Zhou, Li Li, Rui Chen, Soo-Hyun Choi, Xia Hu

However, model editing for graph neural networks (GNNs) is rarely explored, despite GNNs' widespread applicability.

Fake News Detection Model Editing

LMs: Understanding Code Syntax and Semantics for Code Analysis

no code implementations20 May 2023 Wei Ma, Shangqing Liu, ZhiHao Lin, Wenhan Wang, Qiang Hu, Ye Liu, Cen Zhang, Liming Nie, Li Li, Yang Liu

We break down the abilities needed for artificial intelligence~(AI) models to address SE tasks related to code analysis into three categories: 1) syntax understanding, 2) static behavior understanding, and 3) dynamic behavior understanding.

Milestones in Autonomous Driving and Intelligent Vehicles Part I: Control, Computing System Design, Communication, HD Map, Testing, and Human Behaviors

no code implementations12 May 2023 Long Chen, Yuchen Li, Chao Huang, Yang Xing, Daxin Tian, Li Li, Zhongxu Hu, Siyu Teng, Chen Lv, Jinjun Wang, Dongpu Cao, Nanning Zheng, Fei-Yue Wang

Our work is divided into 3 independent articles and the first part is a Survey of Surveys (SoS) for total technologies of AD and IVs that involves the history, summarizes the milestones, and provides the perspectives, ethics, and future research directions.

Autonomous Driving Ethics

VPGTrans: Transfer Visual Prompt Generator across LLMs

1 code implementation NeurIPS 2023 Ao Zhang, Hao Fei, Yuan YAO, Wei Ji, Li Li, Zhiyuan Liu, Tat-Seng Chua

While developing a new multimodal LLM (MLLM) by pre-training on tremendous image-text pairs from scratch can be exceedingly resource-consuming, connecting an existing LLM with a comparatively lightweight visual prompt generator (VPG) becomes a feasible paradigm.

Transfer Learning

A Multiagent CyberBattleSim for RL Cyber Operation Agents

no code implementations3 Apr 2023 Thomas Kunz, Christian Fisher, James La Novara-Gsell, Christopher Nguyen, Li Li

In particular, training a blue agent jointly with a red agent increases the blue agent's capability to thwart sophisticated red agents.

CyberBattleSim Reinforcement Learning (RL)

Enabling A Network AI Gym for Autonomous Cyber Agents

no code implementations3 Apr 2023 Li Li, Jean-Pierre S. El Rami, Adrian Taylor, James Hailing Rao, Thomas Kunz

This work aims to enable autonomous agents for network cyber operations (CyOps) by applying reinforcement and deep reinforcement learning (RL/DRL).

Offline RL Reinforcement Learning (RL)

Unified Emulation-Simulation Training Environment for Autonomous Cyber Agents

no code implementations3 Apr 2023 Li Li, Jean-Pierre S. El Rami, Adrian Taylor, James Hailing Rao, Thomas Kunz

This work presents a systematic solution to automatically generate a high-fidelity simulator in the Cyber Gym for Intelligent Learning (CyGIL).

Offline RL Reinforcement Learning (RL) +1

Milestones in Autonomous Driving and Intelligent Vehicles: Survey of Surveys

no code implementations30 Mar 2023 Long Chen, Yuchen Li, Chao Huang, Bai Li, Yang Xing, Daxin Tian, Li Li, Zhongxu Hu, Xiaoxiang Na, Zixuan Li, Siyu Teng, Chen Lv, Jinjun Wang, Dongpu Cao, Nanning Zheng, Fei-Yue Wang

Interest in autonomous driving (AD) and intelligent vehicles (IVs) is growing at a rapid pace due to the convenience, safety, and economic benefits.

Autonomous Driving Ethics

HandNeRF: Neural Radiance Fields for Animatable Interacting Hands

no code implementations CVPR 2023 Zhiyang Guo, Wengang Zhou, Min Wang, Li Li, Houqiang Li

We propose a novel framework to reconstruct accurate appearance and geometry with neural radiance fields (NeRF) for interacting hands, enabling the rendering of photo-realistic images and videos for gesture animation from arbitrary views.

Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation

1 code implementation CVPR 2023 Li Li, Hubert P. H. Shum, Toby P. Breckon

Whilst the availability of 3D LiDAR point cloud data has significantly grown in recent years, annotation remains expensive and time-consuming, leading to a demand for semi-supervised semantic segmentation methods with application domains such as autonomous driving.

 Ranked #1 on 3D Semantic Segmentation on ScribbleKITTI (mIoU-1% metric)

3D Semantic Segmentation Autonomous Driving +3

An Adaptive Plug-and-Play Network for Few-Shot Learning

no code implementations18 Feb 2023 Hao Li, Li Li, Yunmeng Huang, Ning li, Yongtao Zhang

Few-shot learning (FSL) requires a model to classify new samples after learning from only a few samples.

Few-Shot Learning

Denoising and Prompt-Tuning for Multi-Behavior Recommendation

1 code implementation12 Feb 2023 Chi Zhang, Rui Chen, Xiangyu Zhao, Qilong Han, Li Li

In practical recommendation scenarios, users often interact with items under multi-typed behaviors (e. g., click, add-to-cart, and purchase).

Collaborative Filtering Denoising

Neural Characteristic Function Learning for Conditional Image Generation

1 code implementation ICCV 2023 Shengxi Li, Jialu Zhang, Yifei Li, Mai Xu, Xin Deng, Li Li

The emergence of conditional generative adversarial networks (cGANs) has revolutionised the way we approach and control the generation, by means of adversarially learning joint distributions of data and auxiliary information.

Conditional Image Generation Generative Adversarial Network

Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection

1 code implementation23 Dec 2022 Qiaoyu Tan, Xin Zhang, Ninghao Liu, Daochen Zha, Li Li, Rui Chen, Soo-Hyun Choi, Xia Hu

To bridge the gap, we introduce a Personalized Subgraph Selector (PS2) as a plug-and-play framework to automatically, personally, and inductively identify optimal subgraphs for different edges when performing GNNLP.

Link Prediction

CLIP2GAN: Towards Bridging Text with the Latent Space of GANs

no code implementations28 Nov 2022 YiXuan Wang, Wengang Zhou, Jianmin Bao, Weilun Wang, Li Li, Houqiang Li

The key idea of our CLIP2GAN is to bridge the output feature embedding space of CLIP and the input latent space of StyleGAN, which is realized by introducing a mapping network.

Attribute Image Generation +1

Coordinating CAV Swarms at Intersections with a Deep Learning Model

no code implementations10 Nov 2022 Jiawei Zhang, Shen Li, Li Li

Connected and automated vehicles (CAVs) are viewed as a special kind of robots that have the potential to significantly improve the safety and efficiency of traffic.


Phonetic-assisted Multi-Target Units Modeling for Improving Conformer-Transducer ASR system

no code implementations3 Nov 2022 Li Li, Dongxing Xu, Haoran Wei, Yanhua Long

Exploiting effective target modeling units is very important and has always been a concern in end-to-end automatic speech recognition (ASR).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

DeepMLE: A Robust Deep Maximum Likelihood Estimator for Two-view Structure from Motion

no code implementations11 Oct 2022 Yuxi Xiao, Li Li, Xiaodi Li, Jian Yao

In addition, in order to increase the robustness of our framework, we formulate the likelihood function of the correlations of 2D image matches as a Gaussian and Uniform mixture distribution which takes the uncertainty caused by illumination changes, image noise and moving objects into account.

3D Reconstruction

Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems

no code implementations13 Sep 2022 Zhensu Sun, Xiaoning Du, Fu Song, Shangwen Wang, Mingze Ni, Li Li

The experimental results show that the proposed estimator helps save 23. 3% of computational cost measured in floating-point operations for the code completion systems, and 80. 2% of rejected prompts lead to unhelpful completion

Code Completion

Improved Fuzzy $H_{\infty}$ Filter Design Method for Nonlinear Systems with Time-Varing Delay

no code implementations12 Sep 2022 Qianqian Ma, Li Li, Junhui Shen, Haowei Guan, Guangcheng Ma, Hongwei Xia

This paper investigates the fuzzy $H_{\infty}$ filter design issue for nonlinear systems with time-varying delay.

A New Fuzzy $H_{\infty}$ Filter Design for Nonlinear Time-Delay Systems with Mismatched Premise Membership Functions

no code implementations12 Sep 2022 Qianqian Ma, Hongwei Xia, Li Li, Guangcheng Ma

This paper is concerned with the fuzzy $H_{\infty}$ filter design issue for nonlinear systems with time-varying delay.

Energy Minimization in RIS-Assisted UAV-Enabled Wireless Power Transfer Systems

no code implementations18 Aug 2022 Hong Ren, Zhenkun Zhang, Zhangjie Peng, Li Li, Cunhua Pan

Then, we investigate the general scenario in which the RF signals are radiated during the flight, aiming to minimize the total energy consumption of the UAV by jointly optimizing the UAV's trajectory, flight time and the RIS's reflection coefficients.

Total Energy

Towards Hybrid-Optimization Video Coding

no code implementations12 Jul 2022 Shuai Huo, Dong Liu, Li Li, Siwei Ma, Feng Wu, Wen Gao

Our idea is to provide multiple discrete starting points in the global space and optimize the local optimum around each point by numerical algorithm efficiently.

Piecewise Linear Neural Networks and Deep Learning

no code implementations18 Jun 2022 Qinghua Tao, Li Li, Xiaolin Huang, Xiangming Xi, Shuning Wang, Johan A. K. Suykens

To apply PWLNN methods, both the representation and the learning have long been studied.

CODE-MVP: Learning to Represent Source Code from Multiple Views with Contrastive Pre-Training

no code implementations Findings (NAACL) 2022 Xin Wang, Yasheng Wang, Yao Wan, Jiawei Wang, Pingyi Zhou, Li Li, Hao Wu, Jin Liu

Specifically, we first extract multiple code views using compiler tools, and learn the complementary information among them under a contrastive learning framework.

Contrastive Learning Defect Detection +2

Multiple EffNet/ResNet Architectures for Melanoma Classification

no code implementations21 Apr 2022 Jiaqi Xue, Chentian Ma, Li Li, Xuan Wen

Melanoma is the most malignant skin tumor and usually cancerates from normal moles, which is difficult to distinguish benign from malignant in the early stage.

Classification Image Classification

Image Captioning In the Transformer Age

1 code implementation15 Apr 2022 Yang Xu, Li Li, Haiyang Xu, Songfang Huang, Fei Huang, Jianfei Cai

This drawback inspires the researchers to develop a homogeneous architecture that facilitates end-to-end training, for which Transformer is the perfect one that has proven its huge potential in both vision and language domains and thus can be used as the basic component of the visual encoder and language decoder in an IC pipeline.

Image Captioning Self-Supervised Learning

FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction

1 code implementation CVPR 2022 Liang Gao, Huazhu Fu, Li Li, YingWen Chen, Ming Xu, Cheng-Zhong Xu

Federated learning (FL) allows multiple clients to collectively train a high-performance global model without sharing their private data.

Federated Learning Image Classification

aiWave: Volumetric Image Compression with 3-D Trained Affine Wavelet-like Transform

no code implementations11 Mar 2022 Dongmei Xue, Haichuan Ma, Li Li, Dong Liu, Zhiwei Xiong

Volumetric image compression has become an urgent task to effectively transmit and store images produced in biological research and clinical practice.

Image Compression

Evolving symbolic density functionals

1 code implementation3 Mar 2022 He Ma, Arunachalam Narayanaswamy, Patrick Riley, Li Li

Systematic development of accurate density functionals has been a decades-long challenge for scientists.

On the Importance of Building High-quality Training Datasets for Neural Code Search

1 code implementation14 Feb 2022 Zhensu Sun, Yan Liu, Xiaoning Du, Li Li

The performance of neural code search is significantly influenced by the quality of the training data from which the neural models are derived.

Code Search Retrieval

Towards understanding retrosynthesis by energy-based models

no code implementations NeurIPS 2021 Ruoxi Sun, Hanjun Dai, Li Li, Steven Kearnes, Bo Dai

In this paper, we propose a framework that unifies sequence- and graph-based methods as energy-based models (EBMs) with different energy functions.

Drug Discovery Retrosynthesis

DurLAR: A High-Fidelity 128-Channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-Modal Autonomous Driving Applications

1 code implementation International Conference on 3D Vision (3DV) 2021 Li Li, Khalid N. Ismail, Hubert P. H. Shum, Toby P. Breckon

Leveraging DurLAR, with a resolution exceeding that of prior benchmarks, we consider the task of monocular depth estimation and use this increased avail- ability of higher resolution, yet sparse ground truth scene depth information to propose a novel joint supervised/self- supervised loss formulation.

Autonomous Driving Monocular Depth Estimation

Attribute Artifacts Removal for Geometry-based Point Cloud Compression

no code implementations1 Dec 2021 Xihua Sheng, Li Li, Dong Liu, Zhiwei Xiong

In this paper, we propose a Multi-Scale Graph Attention Network (MS-GAT) to remove the artifacts of point cloud attributes compressed by G-PCC.

Attribute Graph Attention +2

Temporal Context Mining for Learned Video Compression

1 code implementation27 Nov 2021 Xihua Sheng, Jiahao Li, Bin Li, Li Li, Dong Liu, Yan Lu

From the stored propagated features, we propose to learn multi-scale temporal contexts, and re-fill the learned temporal contexts into the modules of our compression scheme, including the contextual encoder-decoder, the frame generator, and the temporal context encoder.


Distributed Policy Gradient with Variance Reduction in Multi-Agent Reinforcement Learning

no code implementations25 Nov 2021 Xiaoxiao Zhao, Jinlong Lei, Li Li, Jie Chen

This paper studies a distributed policy gradient in collaborative multi-agent reinforcement learning (MARL), where agents over a communication network aim to find the optimal policy to maximize the average of all agents' local returns.

Multi-agent Reinforcement Learning reinforcement-learning +2

MFNet: Multi-class Few-shot Segmentation Network with Pixel-wise Metric Learning

no code implementations30 Oct 2021 Miao Zhang, Miaojing Shi, Li Li

Last, to enhance the embedding space learning, an additional pixel-wise metric learning module is introduced with triplet loss formulated on the pixel-level embedding of the input image.

Few-Shot Semantic Segmentation Image Classification +3

How Well Does Kohn-Sham Regularizer Work for Weakly Correlated Systems?

no code implementations28 Oct 2021 Bhupalee Kalita, Ryan Pederson, Jielun Chen, Li Li, Kieron Burke

Kohn-Sham regularizer (KSR) is a differentiable machine learning approach to finding the exchange-correlation functional in Kohn-Sham density functional theory (DFT) that works for strongly correlated systems.

BIG-bench Machine Learning Total Energy

CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning

1 code implementation25 Oct 2021 Zhensu Sun, Xiaoning Du, Fu Song, Mingze Ni, Li Li

Github Copilot, trained on billions of lines of public code, has recently become the buzzword in the computer science research and practice community.

Data Poisoning

End-to-End Image Compression with Probabilistic Decoding

no code implementations30 Sep 2021 Haichuan Ma, Dong Liu, Cunhui Dong, Li Li, Feng Wu

However, this nature was seldom considered in previous studies on image compression, which usually chose one possible image as reconstruction, e. g. the one with the maximal a posteriori probability.

Image Compression

EXACT: Scalable Graph Neural Networks Training via Extreme Activation Compression

no code implementations ICLR 2022 Zirui Liu, Kaixiong Zhou, Fan Yang, Li Li, Rui Chen, Xia Hu

Based on the implementation, we propose a memory-efficient framework called ``EXACT'', which for the first time demonstrate the potential and evaluate the feasibility of training GNNs with compressed activations.

Graph Learning

FedDrop: Trajectory-weighted Dropout for Efficient Federated Learning

no code implementations29 Sep 2021 Dongping Liao, Xitong Gao, Yiren Zhao, Hao Dai, Li Li, Kafeng Wang, Kejiang Ye, Yang Wang, Cheng-Zhong Xu

Federated learning (FL) enables edge clients to train collaboratively while preserving individual's data privacy.

Federated Learning

An Information Fusion Approach to Learning with Instance-Dependent Label Noise

no code implementations ICLR 2022 Zhimeng Jiang, Kaixiong Zhou, Zirui Liu, Li Li, Rui Chen, Soo-Hyun Choi, Xia Hu

Instance-dependent label noise (IDN) widely exists in real-world datasets and usually misleads the training of deep neural networks.

iWave3D: End-to-end Brain Image Compression with Trainable 3-D Wavelet Transform

no code implementations18 Sep 2021 Dongmei Xue, Haichuan Ma, Li Li, Dong Liu, Zhiwei Xiong

With the rapid development of whole brain imaging technology, a large number of brain images have been produced, which puts forward a great demand for efficient brain image compression methods.

Image Compression

CyGIL: A Cyber Gym for Training Autonomous Agents over Emulated Network Systems

no code implementations7 Sep 2021 Li Li, Raed Fayad, Adrian Taylor

Given the success of reinforcement learning (RL) in various domains, it is promising to explore the application of its methods to the development of intelligent and autonomous cyber agents.

Reinforcement Learning (RL)

On Faster Convergence of Scaled Sign Gradient Descent

no code implementations4 Sep 2021 Xiuxian Li, Kuo-Yi Lin, Li Li, Yiguang Hong, Jie Chen

For the first two cases, it can be shown that the scaled signGD converges at a linear rate.

Adaptive Label Smoothing To Regularize Large-Scale Graph Training

no code implementations30 Aug 2021 Kaixiong Zhou, Ninghao Liu, Fan Yang, Zirui Liu, Rui Chen, Li Li, Soo-Hyun Choi, Xia Hu

Graph neural networks (GNNs), which learn the node representations by recursively aggregating information from its neighbors, have become a predominant computational tool in many domains.

Node Clustering

SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation

no code implementations10 Aug 2021 Xin Wang, Yasheng Wang, Fei Mi, Pingyi Zhou, Yao Wan, Xiao Liu, Li Li, Hao Wu, Jin Liu, Xin Jiang

Code representation learning, which aims to encode the semantics of source code into distributed vectors, plays an important role in recent deep-learning-based models for code intelligence.

Clone Detection Code Search +5

Bayesian forecast combination using time-varying features

no code implementations4 Aug 2021 Li Li, Yanfei Kang, Feng Li

In this work, we propose a novel framework for density forecast combination by constructing time-varying weights based on time series features, which is called Feature-based Bayesian Forecasting Model Averaging (FEBAMA).

Time Series Time Series Analysis +1

Dirichlet Energy Constrained Learning for Deep Graph Neural Networks

1 code implementation NeurIPS 2021 Kaixiong Zhou, Xiao Huang, Daochen Zha, Rui Chen, Li Li, Soo-Hyun Choi, Xia Hu

To this end, we analyze the bottleneck of deep GNNs by leveraging the Dirichlet energy of node embeddings, and propose a generalizable principle to guide the training of deep GNNs.

Federated Noisy Client Learning

1 code implementation24 Jun 2021 Kahou Tam, Li Li, Bo Han, Chengzhong Xu, Huazhu Fu

Federated learning (FL) collaboratively trains a shared global model depending on multiple local clients, while keeping the training data decentralized in order to preserve data privacy.

Federated Learning

Composition and Application of Current Advanced Driving Assistance System: A Review

no code implementations26 May 2021 Xinran Li, Kuo-Yi Lin, Min Meng, Xiuxian Li, Li Li, Yiguang Hong, Jie Chen

Due to the growing awareness of driving safety and the development of sophisticated technologies, advanced driving assistance system (ADAS) has been equipped in more and more vehicles with higher accuracy and lower price.

Drill the Cork of Information Bottleneck by Inputting the Most Important Data

no code implementations15 May 2021 Xinyu Peng, Jiawei Zhang, Fei-Yue Wang, Li Li

As a promising tool to better understand the learning dynamic of minibatch SGD, the information bottleneck (IB) theory claims that the optimization process consists of an initial fitting phase and the following compression phase.

Unsupervised domain adaptation via double classifiers based on high confidence pseudo label

no code implementations11 May 2021 Huihuang Chen, Li Li, Jie Chen, Kuo-Yi Lin

In addition to aligning the global distribution, the real domain adaptation should also align the meso distribution and the micro distribution.

Pseudo Label Transfer Learning +1

Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions

1 code implementation22 Apr 2021 Jing Wu, Mingyi Zhou, Ce Zhu, Yipeng Liu, Mehrtash Harandi, Li Li

Recently, adversarial attack methods have been developed to challenge the robustness of machine learning models.

Adversarial Attack

Distributed Cooperative Driving in Multi-Intersection Road Networks

no code implementations21 Apr 2021 Huaxin Pei, Yi Zhang, Qinghua Tao, Shuo Feng, Li Li

Cooperative driving at isolated intersections attracted great interest and had been well discussed in recent years.

CSAFL: A Clustered Semi-Asynchronous Federated Learning Framework

no code implementations16 Apr 2021 Yu Zhang, Moming Duan, Duo Liu, Li Li, Ao Ren, Xianzhang Chen, Yujuan Tan, Chengliang Wang

Asynchronous FL has a natural advantage in mitigating the straggler effect, but there are threats of model quality degradation and server crash.

Federated Learning

Density-aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement

no code implementations11 Mar 2021 Chi Zhang, Zihang Lin, Liheng Xu, Zongliang Li, Wei Tang, Yuehu Liu, Gaofeng Meng, Le Wang, Li Li

The key procedure of haze image translation through adversarial training lies in the disentanglement between the feature only involved in haze synthesis, i. e. style feature, and the feature representing the invariant semantic content, i. e. content feature.

Disentanglement Image Generation +1

Deep Learning for Android Malware Defenses: a Systematic Literature Review

1 code implementation9 Mar 2021 Yue Liu, Chakkrit Tantithamthavorn, Li Li, Yepang Liu

In this paper, we conducted a systematic literature review to search and analyze how deep learning approaches have been applied in the context of malware defenses in the Android environment.

Android Malware Detection Malware Detection +2

Restoring Execution Environments of Jupyter Notebooks

1 code implementation4 Mar 2021 Jiawei Wang, Li Li, Andreas Zeller

More than ninety percent of published Jupyter notebooks do not state dependencies on external packages.

Software Engineering

Distributed quantum phase estimation with entangled photons

no code implementations23 Feb 2021 Li-Zheng Liu, Yu-Zhe Zhang, Zheng-Da Li, Rui Zhang, Xu-Fei Yin, Yue-Yang Fei, Li Li, Nai-Le Liu, Feihu Xu, Yu-Ao Chen, Jian-Wei Pan

Distributed quantum metrology can enhance the sensitivity for sensing spatially distributed parameters beyond the classical limits.

Quantum Physics

DEAL: Decremental Energy-Aware Learning in a Federated System

no code implementations5 Feb 2021 Wenting Zou, Li Li, Zichen Xu, Chengzhong Xu

To address the conflict between learning SLO and energy efficiency, we propose DEAL, an energy efficient learning system that saves energy and preserves privacy with a decremental learning design.

energy management Federated Learning +1

A 3D Non-stationary MmWave Channel Model for Vacuum Tube Ultra-High-Speed Train Channels

no code implementations17 Jan 2021 YingJie Xu, Kai Yu, Li Li, Xianfu Lei, Li Hao, Cheng-Xiang Wang

As a potential development direction of future transportation, the vacuum tube ultra-high-speed train (UHST) wireless communication systems have newly different channel characteristics from existing high-speed train (HST) scenarios.

Offline Meta-level Model-based Reinforcement Learning Approach for Cold-Start Recommendation

no code implementations4 Dec 2020 Yanan Wang, Yong Ge, Li Li, Rui Chen, Tong Xu

To improve adaptation efficiency, we learn to recover the user policy and reward from only a few interactions via an inverse reinforcement learning method to assist a meta-level recommendation agent.

Model-based Reinforcement Learning Recommendation Systems +2

Learnability and Complexity of Quantum Samples

1 code implementation22 Oct 2020 Murphy Yuezhen Niu, Andrew M. Dai, Li Li, Augustus Odena, Zhengli Zhao, Vadim Smelyanskyi, Hartmut Neven, Sergio Boixo

Given a quantum circuit, a quantum computer can sample the output distribution exponentially faster in the number of bits than classical computers.


Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics

1 code implementation17 Sep 2020 Li Li, Stephan Hoyer, Ryan Pederson, Ruoxi Sun, Ekin D. Cubuk, Patrick Riley, Kieron Burke

Including prior knowledge is important for effective machine learning models in physics, and is usually achieved by explicitly adding loss terms or constraints on model architectures.

BIG-bench Machine Learning

Explainable Recommender Systems via Resolving Learning Representations

no code implementations21 Aug 2020 Ninghao Liu, Yong Ge, Li Li, Xia Hu, Rui Chen, Soo-Hyun Choi

Different from previous work, in our model, factor discovery and representation learning are simultaneously conducted, and we are able to handle extra attribute information and knowledge.

Attribute Explainable Recommendation +2

Defending Adversarial Examples via DNN Bottleneck Reinforcement

no code implementations12 Aug 2020 Wenqing Liu, Miaojing Shi, Teddy Furon, Li Li

This paper presents a DNN bottleneck reinforcement scheme to alleviate the vulnerability of Deep Neural Networks (DNN) against adversarial attacks.

Energy-based View of Retrosynthesis

no code implementations14 Jul 2020 Ruoxi Sun, Hanjun Dai, Li Li, Steven Kearnes, Bo Dai

Retrosynthesis -- the process of identifying a set of reactants to synthesize a target molecule -- is of vital importance to material design and drug discovery.

Drug Discovery Retrosynthesis +1

Scaling Symbolic Methods using Gradients for Neural Model Explanation

2 code implementations ICLR 2021 Subham Sekhar Sahoo, Subhashini Venugopalan, Li Li, Rishabh Singh, Patrick Riley

In this work, we propose a technique for combining gradient-based methods with symbolic techniques to scale such analyses and demonstrate its application for model explanation.

A Real-Time Dispatching Strategy for Shared Automated Electric Vehicles with Performance Guarantees

no code implementations28 Jun 2020 Li Li, Theodoros Pantelidis, Joseph Y. J. Chow, Saif Eddin Jabari

To overcome this complexity, we employ an online minimum drift plus penalty (MDPP) approach for SAEV systems that (i) does not require a priori knowledge of customer arrival rates to the different parts of the system (i. e. it is practical from a real-world deployment perspective), (ii) ensures the stability of customer waiting times, (iii) ensures that the deviation of dispatch costs from a desirable dispatch cost can be controlled, and (iv) has a computational time-complexity that allows for real-time implementation.


Multiuser Full-Duplex Two-Way Communications via Intelligent Reflecting Surface

no code implementations9 Jun 2020 Zhangjie Peng, Zhenkun Zhang, Cunhua Pan, Li Li, A. Lee Swindlehurst

Low-cost passive intelligent reflecting surfaces (IRSs) have recently been envisioned as a revolutionary technology capable of reconfiguring the wireless propagation environment through carefully tuning reflection elements.

Fairness Vocal Bursts Valence Prediction

Investigating Quantum Approximate Optimization Algorithms under Bang-bang Protocols

1 code implementation27 May 2020 Daniel Liang, Li Li, Stefan Leichenauer

The quantum approximate optimization algorithm (QAOA) is widely seen as a possible usage of noisy intermediate-scale quantum (NISQ) devices.

Quantum Physics

A Framework for Behavioral Biometric Authentication using Deep Metric Learning on Mobile Devices

no code implementations26 May 2020 Cong Wang, Yanru Xiao, Xing Gao, Li Li, Jun Wang

We show the feasibility of training with mobile CPUs, where training 100 epochs takes less than 10 mins and can be boosted 3-5 times with feature transfer.

Metric Learning Multi-class Classification

Warwick Image Forensics Dataset for Device Fingerprinting In Multimedia Forensics

no code implementations22 Apr 2020 Yijun Quan, Chang-Tsun Li, Yujue Zhou, Li Li

Device fingerprints like sensor pattern noise (SPN) are widely used for provenance analysis and image authentication.

Image Forensics

Incorporating Multiple Cluster Centers for Multi-Label Learning

no code implementations17 Apr 2020 Senlin Shu, Fengmao Lv, Yan Yan, Li Li, Shuo He, Jun He

In this article, we propose to leverage the data augmentation technique to improve the performance of multi-label learning.

Clustering Data Augmentation +1

Vanishing Point Guided Natural Image Stitching

no code implementations6 Apr 2020 Kai Chen, Jian Yao, Jingmin Tu, Yahui Liu, Yinxuan Li, Li Li

Recently, works on improving the naturalness of stitching images gain more and more extensive attention.

Image Stitching

Developing Multi-Task Recommendations with Long-Term Rewards via Policy Distilled Reinforcement Learning

no code implementations27 Jan 2020 Xi Liu, Li Li, Ping-Chun Hsieh, Muhe Xie, Yong Ge, Rui Chen

With the explosive growth of online products and content, recommendation techniques have been considered as an effective tool to overcome information overload, improve user experience, and boost business revenue.

Knowledge Distillation Multi-Task Learning +2

Diversifying Topic-Coherent Response Generation for Natural Multi-turn Conversations

no code implementations24 Oct 2019 Fei Hu, Wei Liu, Ajmal Saeed Mian, Li Li

In this paper, we propose the Topic-coherent Hierarchical Recurrent Encoder-Decoder model (THRED) to diversify the generated responses without deviating the contextual topics for multi-turn conversations.

Response Generation

An Improved Historical Embedding without Alignment

no code implementations19 Oct 2019 Xiaofei Xu, Ke Deng, Fei Hu, Li Li

Our method outperformed three other popular methods in terms of the number of words correctly identified to have changed in meaning.

Word Embeddings

Residual-Guided In-Loop Filter Using Convolution Neural Network

no code implementations29 Jul 2019 Wei Jia, Li Li, Zhu Li, Xiang Zhang, Shan Liu

The block-based coding structure in the hybrid video coding framework inevitably introduces compression artifacts such as blocking, ringing, etc.


Click-Through Rate Prediction with the User Memory Network

1 code implementation9 Jul 2019 Wentao Ouyang, Xiuwu Zhang, Shukui Ren, Li Li, Zhaojie Liu, Yanlong Du

Both offline and online experiments demonstrate the effectiveness of MA-DNN for practical CTR prediction services.

Click-Through Rate Prediction

Cooperative Lane Changing via Deep Reinforcement Learning

no code implementations20 Jun 2019 Guan Wang, Jianming Hu, Zhiheng Li, Li Li

In this paper, we study how to learn an appropriate lane changing strategy for autonomous vehicles by using deep reinforcement learning.

Autonomous Vehicles reinforcement-learning +1

Deep Spatio-Temporal Neural Networks for Click-Through Rate Prediction

1 code implementation10 Jun 2019 Wentao Ouyang, Xiuwu Zhang, Li Li, Heng Zou, Xin Xing, Zhaojie Liu, Yanlong Du

The intuitions are that ads shown together may influence each other, clicked ads reflect a user's preferences, and unclicked ads may indicate what a user dislikes to certain extent.

Click-Through Rate Prediction

Decoding Molecular Graph Embeddings with Reinforcement Learning

no code implementations18 Apr 2019 Steven Kearnes, Li Li, Patrick Riley

We present RL-VAE, a graph-to-graph variational autoencoder that uses reinforcement learning to decode molecular graphs from latent embeddings.

Graph Matching reinforcement-learning +1

Accelerating Minibatch Stochastic Gradient Descent using Typicality Sampling

no code implementations11 Mar 2019 Xinyu Peng, Li Li, Fei-Yue Wang

Machine learning, especially deep neural networks, has been rapidly developed in fields including computer vision, speech recognition and reinforcement learning.

Reinforcement Learning (RL) speech-recognition +2

Neural-Guided Symbolic Regression with Asymptotic Constraints

1 code implementation23 Jan 2019 Li Li, Minjie Fan, Rishabh Singh, Patrick Riley

The second part, which we call Neural-Guided Monte Carlo Tree Search, uses the network during a search to find an expression that conforms to a set of data points and desired leading powers.

regression Symbolic Regression

Fast MVAE: Joint separation and classification of mixed sources based on multichannel variational autoencoder with auxiliary classifier

no code implementations16 Dec 2018 Li Li, Hirokazu Kameoka, Shoji Makino

While MVAE is notable in its impressive source separation performance, the convergence-guaranteed optimization algorithm and that it allows us to estimate source-class labels simultaneously with source separation, there are still two major drawbacks, i. e., the high computational complexity and unsatisfactory source classification accuracy.

Classification General Classification

Rebooting Research on Detecting Repackaged Android Apps: Literature Review and Benchmark

1 code implementation20 Nov 2018 Li Li, Tegawendé Bissyandé, Jacques Klein

Repackaging is a serious threat to the Android ecosystem as it deprives app developers of their benefits, contributes to spreading malware on users' devices, and increases the workload of market maintainers.

Software Engineering

An Orchestrated Empirical Study on Deep Learning Frameworks and Platforms

no code implementations13 Nov 2018 Qianyu Guo, Xiaofei Xie, Lei Ma, Qiang Hu, Ruitao Feng, Li Li, Yang Liu, Jianjun Zhao, Xiaohong Li

Up to the present, it still lacks a comprehensive study on how current diverse DL frameworks and platforms influence the DL software development process.

Autonomous Driving

Optimization of Molecules via Deep Reinforcement Learning

7 code implementations19 Oct 2018 Zhenpeng Zhou, Steven Kearnes, Li Li, Richard N. Zare, Patrick Riley

We present a framework, which we call Molecule Deep $Q$-Networks (MolDQN), for molecule optimization by combining domain knowledge of chemistry and state-of-the-art reinforcement learning techniques (double $Q$-learning and randomized value functions).

 Ranked #1 on Molecular Graph Generation on ZINC (QED Top-3 metric)

Molecular Graph Generation Multi-Objective Reinforcement Learning +2

Multiple Combined Constraints for Image Stitching

no code implementations18 Sep 2018 Kai Chen, Jingmin Tu, Binbin Xiang, Li Li, Jian Yao

In this paper, geometric and photometric constraints are combined to improve the alignment quality, which is based on the observation that these two kinds of constraints are complementary.

Image Stitching

Learning Data-adaptive Nonparametric Kernels

no code implementations31 Aug 2018 Fanghui Liu, Xiaolin Huang, Chen Gong, Jie Yang, Li Li

Learning this data-adaptive matrix in a formulation-free strategy enlarges the margin between classes and thus improves the model flexibility.

An Efficient Deep Reinforcement Learning Model for Urban Traffic Control

1 code implementation6 Aug 2018 Yilun Lin, Xingyuan Dai, Li Li, Fei-Yue Wang

Urban Traffic Control (UTC) plays an essential role in Intelligent Transportation System (ITS) but remains difficult.

reinforcement-learning Reinforcement Learning (RL)

Semi-blind source separation with multichannel variational autoencoder

1 code implementation2 Aug 2018 Hirokazu Kameoka, Li Li, Shota Inoue, Shoji Makino

This paper proposes a multichannel source separation technique called the multichannel variational autoencoder (MVAE) method, which uses a conditional VAE (CVAE) to model and estimate the power spectrograms of the sources in a mixture.

blind source separation

DeepMutation: Mutation Testing of Deep Learning Systems

4 code implementations14 May 2018 Lei Ma, Fuyuan Zhang, Jiyuan Sun, Minhui Xue, Bo Li, Felix Juefei-Xu, Chao Xie, Li Li, Yang Liu, Jianjun Zhao, Yadong Wang

To do this, by sharing the same spirit of mutation testing in traditional software, we first define a set of source-level mutation operators to inject faults to the source of DL (i. e., training data and training programs).

Software Engineering

DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems

no code implementations20 Mar 2018 Lei Ma, Felix Juefei-Xu, Fuyuan Zhang, Jiyuan Sun, Minhui Xue, Bo Li, Chunyang Chen, Ting Su, Li Li, Yang Liu, Jianjun Zhao, Yadong Wang

Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data.

Adversarial Attack Defect Detection

Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds

3 code implementations22 Feb 2018 Nathaniel Thomas, Tess Smidt, Steven Kearnes, Lusann Yang, Li Li, Kai Kohlhoff, Patrick Riley

We introduce tensor field neural networks, which are locally equivariant to 3D rotations, translations, and permutations of points at every layer.

Data Augmentation Translation

Demonstration of Topological Data Analysis on a Quantum Processor

no code implementations19 Jan 2018 He-Liang Huang, Xi-Lin Wang, Peter P. Rohde, Yi-Han Luo, You-Wei Zhao, Chang Liu, Li Li, Nai-Le Liu, Chao-Yang Lu, Jian-Wei Pan

Topological data analysis offers a robust way to extract useful information from noisy, unstructured data by identifying its underlying structure.

Topological Data Analysis

Improving Malware Detection Accuracy by Extracting Icon Information

1 code implementation10 Dec 2017 Pedro Silva, Sepehr Akhavan-Masouleh, Li Li

While these models commonly use features extracted from the structure of PE files, we propose that icons from these files can also help better predict malware.

BIG-bench Machine Learning Clustering +1

Lazy stochastic principal component analysis

1 code implementation21 Sep 2017 Michael Wojnowicz, Dinh Nguyen, Li Li, Xuan Zhao

Stochastic principal component analysis (SPCA) has become a popular dimensionality reduction strategy for large, high-dimensional datasets.

Dimensionality Reduction

DeepTrend: A Deep Hierarchical Neural Network for Traffic Flow Prediction

no code implementations11 Jul 2017 Xingyuan Dai, Rui Fu, Yilun Lin, Li Li, Fei-Yue Wang

Detrending based methods decompose original flow series into trend and residual series, in which trend describes the fixed temporal pattern in traffic flow and residual series is used for prediction.

Time Series Time Series Analysis

Learning to Refine Object Contours with a Top-Down Fully Convolutional Encoder-Decoder Network

no code implementations12 May 2017 Yahui Liu, Jian Yao, Li Li, Xiaohu Lu, Jing Han

We develop a novel deep contour detection algorithm with a top-down fully convolutional encoder-decoder network.

Contour Detection

Convolutional Neural Network-Based Block Up-sampling for Intra Frame Coding

no code implementations22 Feb 2017 Yue Li, Dong Liu, Houqiang Li, Li Li, Feng Wu, Hong Zhang, Haitao Yang

A block can be down-sampled before being compressed by normal intra coding, and then up-sampled to its original resolution.


Projection based advanced motion model for cubic mapping for 360-degree video

no code implementations21 Feb 2017 Li Li, Zhu Li, Madhukar Budagavi, Houqiang Li

This paper proposes a novel advanced motion model to handle the irregular motion for the cubic map projection of 360-degree video.

Maximizing Investment Value of Small-Scale PV in a Smart Grid Environment

no code implementations3 Nov 2016 Jeremy Every, Li Li, Youguang G. Guo, David G. Dorrell

Determining the optimal size and orientation of small-scale residential based PV arrays will become increasingly complex in the future smart grid environment with the introduction of smart meters and dynamic tariffs.

By-passing the Kohn-Sham equations with machine learning

2 code implementations9 Sep 2016 Felix Brockherde, Leslie Vogt, Li Li, Mark E. Tuckerman, Kieron Burke, Klaus-Robert Müller

Last year, at least 30, 000 scientific papers used the Kohn-Sham scheme of density functional theory to solve electronic structure problems in a wide variety of scientific fields, ranging from materials science to biochemistry to astrophysics.

BIG-bench Machine Learning

Watch out for This Commit! A Study of Influential Software Changes

no code implementations10 Jun 2016 Daoyuan Li, Li Li, Dongsun Kim, Tegawendé F. Bissyandé, David Lo, Yves Le Traon

One single code change can significantly influence a wide range of software systems and their users.

Software Engineering

Towards Label Imbalance in Multi-label Classification with Many Labels

no code implementations5 Apr 2016 Li Li, Houfeng Wang

To the best of our knowledge, we are the first to tackle the imbalance problem in multi-label classification with many labels.

Classification General Classification +2