Search Results for author: Jie Wang

Found 163 papers, 49 papers with code

On Explainability of Graph Neural Networks via Subgraph Explorations

1 code implementation9 Feb 2021 Hao Yuan, Haiyang Yu, Jie Wang, Kang Li, Shuiwang Ji

To make the tree search more effective, we propose to use Shapley values as a measure of subgraph importance, which can also capture the interactions among different subgraphs.

FlowX: Towards Explainable Graph Neural Networks via Message Flows

2 code implementations26 Jun 2022 Shurui Gui, Hao Yuan, Jie Wang, Qicheng Lao, Kang Li, Shuiwang Ji

We investigate the explainability of graph neural networks (GNNs) as a step toward elucidating their working mechanisms.

Philosophy

An Intuitive Tutorial to Gaussian Process Regression

3 code implementations22 Sep 2020 Jie Wang

This tutorial is accessible to a broad audience, including those new to machine learning, ensuring a clear understanding of GPR fundamentals.

BIG-bench Machine Learning GPR +1

WeKws: A production first small-footprint end-to-end Keyword Spotting Toolkit

1 code implementation30 Oct 2022 Jie Wang, Menglong Xu, Jingyong Hou, BinBin Zhang, Xiao-Lei Zhang, Lei Xie, Fuping Pan

Keyword spotting (KWS) enables speech-based user interaction and gradually becomes an indispensable component of smart devices.

Keyword Spotting

Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control

1 code implementation11 Mar 2019 Tianshu Chu, Jie Wang, Lara Codecà, Zhaojian Li

Reinforcement learning (RL) is a promising data-driven approach for adaptive traffic signal control (ATSC) in complex urban traffic networks, and deep neural networks further enhance its learning power.

Q-Learning reinforcement-learning +1

Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking

1 code implementation CVPR 2021 Ning Wang, Wengang Zhou, Jie Wang, Houqaing Li

In video object tracking, there exist rich temporal contexts among successive frames, which have been largely overlooked in existing trackers.

Object Video Object Tracking +2

GaussianHead: High-fidelity Head Avatars with Learnable Gaussian Derivation

1 code implementation4 Dec 2023 Jie Wang, Jiu-Cheng Xie, Xianyan Li, Feng Xu, Chi-Man Pun, Hao Gao

Constructing vivid 3D head avatars for given subjects and realizing a series of animations on them is valuable yet challenging.

Novel View Synthesis

Rethinking Graph Convolutional Networks in Knowledge Graph Completion

2 code implementations8 Feb 2022 Zhanqiu Zhang, Jie Wang, Jieping Ye, Feng Wu

Surprisingly, we observe from experiments that the graph structure modeling in GCNs does not have a significant impact on the performance of KGC models, which is in contrast to the common belief.

Entity Embeddings Knowledge Graph Completion +1

De Novo Molecular Generation via Connection-aware Motif Mining

1 code implementation2 Feb 2023 Zijie Geng, Shufang Xie, Yingce Xia, Lijun Wu, Tao Qin, Jie Wang, Yongdong Zhang, Feng Wu, Tie-Yan Liu

The obtained motif vocabulary consists of not only molecular motifs (i. e., the frequent fragments), but also their connection information, indicating how the motifs are connected with each other.

ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs

1 code implementation NeurIPS 2021 Zhanqiu Zhang, Jie Wang, Jiajun Chen, Shuiwang Ji, Feng Wu

To address this challenge, we propose a novel query embedding model, namely Cone Embeddings (ConE), which is the first geometry-based QE model that can handle all the FOL operations, including conjunction, disjunction, and negation.

Knowledge Graphs Negation

LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergence

1 code implementation2 Feb 2023 Zhihao Shi, Xize Liang, Jie Wang

The key idea of LMC is to retrieve the discarded messages in backward passes based on a message passing formulation of backward passes.

Compressing Deep Graph Neural Networks via Adversarial Knowledge Distillation

1 code implementation24 May 2022 Huarui He, Jie Wang, Zhanqiu Zhang, Feng Wu

To tackle these problems, we propose a novel Adversarial Knowledge Distillation framework for graph models named GraphAKD, which adversarially trains a discriminator and a generator to adaptively detect and decrease the discrepancy.

Graph Classification Knowledge Distillation +1

Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs

1 code implementation5 Mar 2021 Jiajun Chen, Huarui He, Feng Wu, Jie Wang

TACT is inspired by the observation that the semantic correlation between two relations is highly correlated to their topological structure in knowledge graphs.

Inductive Link Prediction Knowledge Graphs +1

TSSOS: A Moment-SOS hierarchy that exploits term sparsity

3 code implementations18 Dec 2019 Jie Wang, Victor Magron, Jean-Bernard Lasserre

This paper is concerned with polynomial optimization problems.

Optimization and Control

Chordal-TSSOS: a moment-SOS hierarchy that exploits term sparsity with chordal extension

1 code implementation4 Mar 2020 Jie Wang, Victor Magron, Jean-Bernard Lasserre

The novelty and distinguishing feature of such relaxations is to obtain quasi block-diagonal matrices obtained in an iterative procedure that performs chordal extension of certain adjacency graphs.

Optimization and Control 14P10, 90C25, 12D15, 12Y05

Sparse Polynomial Optimization: Theory and Practice

2 code implementations23 Aug 2022 Victor Magron, Jie Wang

Fortunately, for many applications, we can look at the problem in the eyes and exploit the inherent data structure arising from the cost and constraints describing the problem, for instance sparsity or symmetries.

NineRec: A Benchmark Dataset Suite for Evaluating Transferable Recommendation

1 code implementation14 Sep 2023 JiaQi Zhang, Yu Cheng, Yongxin Ni, Yunzhu Pan, Zheng Yuan, Junchen Fu, Youhua Li, Jie Wang, Fajie Yuan

The development of TransRec has encountered multiple challenges, among which the lack of large-scale, high-quality transfer learning recommendation dataset and benchmark suites is one of the biggest obstacles.

Descriptive Recommendation Systems +1

Line Graph Neural Networks for Link Prediction

2 code implementations20 Oct 2020 Lei Cai, Jundong Li, Jie Wang, Shuiwang Ji

In this formalism, a link prediction problem is converted to a graph classification task.

General Classification Graph Classification +2

SportsTrack: An Innovative Method for Tracking Athletes in Sports Scenes

1 code implementation14 Nov 2022 Jie Wang, Yuzhou Peng, Xiaodong Yang, Ting Wang, YanMing Zhang

The SportsMOT dataset aims to solve multiple object tracking of athletes in different sports scenes such as basketball or soccer.

Multiple Object Tracking

When HLS Meets FPGA HBM: Benchmarking and Bandwidth Optimization

1 code implementation12 Oct 2020 Young-kyu Choi, Yuze Chi, Jie Wang, Licheng Guo, Jason Cong

With the recent release of High Bandwidth Memory (HBM) based FPGA boards, developers can now exploit unprecedented external memory bandwidth.

Hardware Architecture

A Deep Instance Generative Framework for MILP Solvers Under Limited Data Availability

1 code implementation NeurIPS 2023 Zijie Geng, Xijun Li, Jie Wang, Xiao Li, Yongdong Zhang, Feng Wu

In the past few years, there has been an explosive surge in the use of machine learning (ML) techniques to address combinatorial optimization (CO) problems, especially mixed-integer linear programs (MILPs).

Combinatorial Optimization

Modeling Diverse Chemical Reactions for Single-step Retrosynthesis via Discrete Latent Variables

1 code implementation10 Aug 2022 Huarui He, Jie Wang, Yunfei Liu, Feng Wu

The goal of single-step retrosynthesis is to identify the possible reactants that lead to the synthesis of the target product in one reaction.

Drug Discovery Retrosynthesis +1

TrustGuard: GNN-based Robust and Explainable Trust Evaluation with Dynamicity Support

1 code implementation23 Jun 2023 Jie Wang, Zheng Yan, Jiahe Lan, Elisa Bertino, Witold Pedrycz

Among them, the spatial aggregation layer adopts a defense mechanism to robustly aggregate local trust, and the temporal aggregation layer applies an attention mechanism for effective learning of temporal patterns.

Decision Making

Downstream Transformer Generation of Question-Answer Pairs with Preprocessing and Postprocessing Pipelines

1 code implementation15 May 2022 Cheng Zhang, Hao Zhang, Jie Wang

We present a system called TP3 to perform a downstream task of transformers on generating question-answer pairs (QAPs) from a given article.

Scaling Up Sparse Support Vector Machines by Simultaneous Feature and Sample Reduction

1 code implementation ICML 2017 Weizhong Zhang, Bin Hong, Wei Liu, Jieping Ye, Deng Cai, Xiaofei He, Jie Wang

By noting that sparse SVMs induce sparsities in both feature and sample spaces, we propose a novel approach, which is based on accurate estimations of the primal and dual optima of sparse SVMs, to simultaneously identify the inactive features and samples that are guaranteed to be irrelevant to the outputs.

An Efficient End-to-End 3D Voxel Reconstruction based on Neural Architecture Search

1 code implementation27 Feb 2022 Yongdong Huang, Yuanzhan Li, Xulong Cao, Siyu Zhang, Shen Cai, Ting Lu, Jie Wang, Yuqi Liu

However, many previous works employ neural networks with fixed architecture and size to represent different 3D objects, which lead to excessive network parameters for simple objects and limited reconstruction accuracy for complex objects.

Binary Classification Neural Architecture Search +1

PointGL: A Simple Global-Local Framework for Efficient Point Cloud Analysis

1 code implementation22 Jan 2024 Jianan Li, Jie Wang, Tingfa Xu

Efficient analysis of point clouds holds paramount significance in real-world 3D applications.

SvTPM: A Secure and Efficient vTPM in the Cloud

1 code implementation21 May 2019 Juan Wang, Chengyang Fan, Jie Wang, Yueqiang Cheng, Yinqian Zhang, Wenhui Zhang, Peng Liu, Hongxin Hu

In this paper, we present SvTPM, a secure and efficient software-based vTPM implementation based on hardware-rooted Trusted Execution Environment (TEE), providing a whole life cycle protection of vTPMs in the cloud.

Cryptography and Security

Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions

1 code implementation20 May 2022 Rui Yang, Jie Wang, Zijie Geng, Mingxuan Ye, Shuiwang Ji, Bin Li, Feng Wu

Generalization across different environments with the same tasks is critical for successful applications of visual reinforcement learning (RL) in real scenarios.

Reinforcement Learning (RL)

Improving Pseudo Labels With Intra-Class Similarity for Unsupervised Domain Adaptation

1 code implementation25 Jul 2022 Jie Wang, Xiao-Lei Zhang

In this paper, we propose a novel approach to improve the accuracy of the pseudo labels in the target domain.

Unsupervised Domain Adaptation

Contrastive Semantic-Guided Image Smoothing Network

1 code implementation2 Sep 2022 Jie Wang, Yongzhen Wang, Yidan Feng, Lina Gong, Xuefeng Yan, Haoran Xie, Fu Lee Wang, Mingqiang Wei

Image smoothing is a fundamental low-level vision task that aims to preserve salient structures of an image while removing insignificant details.

image smoothing Semantic Segmentation

Generalization in Visual Reinforcement Learning with the Reward Sequence Distribution

1 code implementation19 Feb 2023 Jie Wang, Rui Yang, Zijie Geng, Zhihao Shi, Mingxuan Ye, Qi Zhou, Shuiwang Ji, Bin Li, Yongdong Zhang, Feng Wu

The appealing features of RSD-OA include that: (1) RSD-OA is invariant to visual distractions, as it is conditioned on the predefined subsequent action sequence without task-irrelevant information from transition dynamics, and (2) the reward sequence captures long-term task-relevant information in both rewards and transition dynamics.

reinforcement-learning Reinforcement Learning (RL) +1

Robust Representation Learning by Clustering with Bisimulation Metrics for Visual Reinforcement Learning with Distractions

1 code implementation12 Feb 2023 Qiyuan Liu, Qi Zhou, Rui Yang, Jie Wang

To tackle this problem, we propose a novel clustering-based approach, namely Clustering with Bisimulation Metrics (CBM), which learns robust representations by grouping visual observations in the latent space.

Clustering Reinforcement Learning (RL) +1

Sinkhorn Distributionally Robust Optimization

1 code implementation24 Sep 2021 Jie Wang, Rui Gao, Yao Xie

We study distributionally robust optimization (DRO) with Sinkhorn distance -- a variant of Wasserstein distance based on entropic regularization.

FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited Knowledge

1 code implementation15 Dec 2023 Jiahe Lan, Jie Wang, Baochen Yan, Zheng Yan, Elisa Bertino

Despite the initial success of current audio backdoor attacks, they suffer from the following limitations: (i) Most of them require sufficient knowledge, which limits their widespread adoption.

Backdoor Attack Data Poisoning +2

Deep Model-Based Reinforcement Learning via Estimated Uncertainty and Conservative Policy Optimization

1 code implementation28 Nov 2019 Qi Zhou, Houqiang Li, Jie Wang

In this paper, We propose a Policy Optimization method with Model-Based Uncertainty (POMBU)---a novel model-based approach---that can effectively improve the asymptotic performance using the uncertainty in Q-values.

Model-based Reinforcement Learning reinforcement-learning +1

A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip Design

1 code implementation22 Aug 2023 Zhihai Wang, Lei Chen, Jie Wang, Xing Li, Yinqi Bai, Xijun Li, Mingxuan Yuan, Jianye Hao, Yongdong Zhang, Feng Wu

In particular, we notice that the runtime of the Resub and Mfs2 operators often dominates the overall runtime of LS optimization processes.

Domain Generalization

Variational Representations and Neural Network Estimation of Rényi Divergences

1 code implementation7 Jul 2020 Jeremiah Birrell, Paul Dupuis, Markos A. Katsoulakis, Luc Rey-Bellet, Jie Wang

We further show that this R\'enyi variational formula holds over a range of function spaces; this leads to a formula for the optimizer under very weak assumptions and is also key in our development of a consistency theory for R\'enyi divergence estimators.

Unsupervised Domain Expansion for Visual Categorization

2 code implementations1 Apr 2021 Jie Wang, Kaibin Tian, Dayong Ding, Gang Yang, Xirong Li

In this paper we extend UDA by proposing a new task called unsupervised domain expansion (UDE), which aims to adapt a deep model for the target domain with its unlabeled data, meanwhile maintaining the model's performance on the source domain.

Knowledge Distillation Unsupervised Domain Adaptation +1

OSSAR: Towards Open-Set Surgical Activity Recognition in Robot-assisted Surgery

1 code implementation10 Feb 2024 Long Bai, Guankun Wang, Jie Wang, Xiaoxiao Yang, Huxin Gao, Xin Liang, An Wang, Mobarakol Islam, Hongliang Ren

Existing algorithms dedicated to surgical activity recognition predominantly cater to pre-defined closed-set paradigms, ignoring the challenges of real-world open-set scenarios.

Activity Recognition

Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias

1 code implementation26 Sep 2023 Zhihao Shi, Jie Wang, Fanghua Lu, Hanzhu Chen, Defu Lian, Zheng Wang, Jieping Ye, Feng Wu

The inverse mapping leads to an objective function that is equivalent to that by the joint training, while it can effectively incorporate GNNs in the training phase of NEs against the learning bias.

Representation Learning

DTATG: An Automatic Title Generator based on Dependency Trees

no code implementations1 Oct 2017 Liqun Shao, Jie Wang

We study automatic title generation for a given block of text and present a method called DTATG to generate titles.

Sentence

Efficient and Effective Single-Document Summarizations and A Word-Embedding Measurement of Quality

no code implementations1 Oct 2017 Liqun Shao, Hao Zhang, Ming Jia, Jie Wang

We show that the orderings of the ROUGE and WESM scores of our algorithms are highly comparable, suggesting that WESM may serve as a viable alternative for measuring the quality of a summary.

Clustering Keyword Extraction

Probabilistic graphical model based approach for water mapping using GaoFen-2 (GF-2) high resolution imagery and Landsat 8 time series

no code implementations22 Dec 2016 Luyan Ji, Jie Wang, Xiurui Geng, Peng Gong

Difficulties of water mapping on high resolution data includes: 1) misclassification between water and shadows or other low-reflectance ground objects, which is mostly caused by the spectral similarity within the given band range; 2) small water bodies with size smaller than the spatial resolution of MS image.

Time Series Time Series Analysis

A probabilistic graphical model approach in 30 m land cover mapping with multiple data sources

no code implementations11 Dec 2016 Jie Wang, Luyan Ji, Xiaomeng Huang, Haohuan Fu, Shiming Xu, Cong-Cong Li

Conditional probability distributions were computed based on data quality and reliability by using information selectively.

Time Series Analysis

Large-scale Collaborative Imaging Genetics Studies of Risk Genetic Factors for Alzheimer's Disease Across Multiple Institutions

no code implementations19 Aug 2016 Qingyang Li, Tao Yang, Liang Zhan, Derrek Paul Hibar, Neda Jahanshad, Yalin Wang, Jieping Ye, Paul M. Thompson, Jie Wang

To the best of our knowledge, this is the first successful run of the computationally intensive model selection procedure to learn a consistent model across different institutions without compromising their privacy while ranking the SNPs that may collectively affect AD.

Model Selection

Safe Screening for Multi-Task Feature Learning with Multiple Data Matrices

no code implementations15 May 2015 Jie Wang, Jieping Ye

One of the appealing features of DPC is that: it is safe in the sense that the detected inactive features are guaranteed to have zero coefficients in the solution vectors across all tasks.

Clustering

Lasso Screening Rules via Dual Polytope Projection

no code implementations NeurIPS 2013 Jie Wang, Peter Wonka, Jieping Ye

To improve the efficiency of solving large-scale Lasso problems, El Ghaoui and his colleagues have proposed the SAFE rules which are able to quickly identify the inactive predictors, i. e., predictors that have $0$ components in the solution vector.

Two-Layer Feature Reduction for Sparse-Group Lasso via Decomposition of Convex Sets

no code implementations NeurIPS 2014 Jie Wang, Jieping Ye

Sparse-Group Lasso (SGL) has been shown to be a powerful regression technique for simultaneously discovering group and within-group sparse patterns by using a combination of the $\ell_1$ and $\ell_2$ norms.

Safe Screening With Variational Inequalities and Its Application to LASSO

no code implementations29 Jul 2013 Jun Liu, Zheng Zhao, Jie Wang, Jieping Ye

Safe screening is gaining increasing attention since 1) solving sparse learning formulations usually has a high computational cost especially when the number of features is large and 2) one needs to try several regularization parameters to select a suitable model.

Computational Efficiency feature selection +1

Scaling SVM and Least Absolute Deviations via Exact Data Reduction

no code implementations25 Oct 2013 Jie Wang, Peter Wonka, Jieping Ye

Some appealing features of our screening method are: (1) DVI is safe in the sense that the vectors discarded by DVI are guaranteed to be non-support vectors; (2) the data set needs to be scanned only once to run the screening, whose computational cost is negligible compared to that of solving the SVM problem; (3) DVI is independent of the solvers and can be integrated with any existing efficient solvers.

A Safe Screening Rule for Sparse Logistic Regression

no code implementations NeurIPS 2014 Jie Wang, Jiayu Zhou, Jun Liu, Peter Wonka, Jieping Ye

The l1-regularized logistic regression (or sparse logistic regression) is a widely used method for simultaneous classification and feature selection.

feature selection regression

Efficient Mixed-Norm Regularization: Algorithms and Safe Screening Methods

no code implementations16 Jul 2013 Jie Wang, Jun Liu, Jieping Ye

One key building block of the proposed algorithm is the l1q-regularized Euclidean projection (EP_1q).

Sparse Learning

Semantic WordRank: Generating Finer Single-Document Summarizations

no code implementations12 Sep 2018 Hao Zhang, Jie Wang

We present Semantic WordRank (SWR), an unsupervised method for generating an extractive summary of a single document.

Clustering

Multi-Layer Feature Reduction for Tree Structured Group Lasso via Hierarchical Projection

no code implementations NeurIPS 2015 Jie Wang, Jieping Ye

By a novel hierarchical projection algorithm, MLFre is able to test the nodes independently from any of their ancestor nodes.

Mexican Hat Wavelet Kernel ELM for Multiclass Classification

no code implementations20 Feb 2019 Jie Wang, Yi-Fan Song, Tian-Lei Ma

Kernel extreme learning machine (KELM) is a novel feedforward neural network, which is widely used in classification problems.

Classification General Classification

An Efficient Pre-processing Method to Eliminate Adversarial Effects

no code implementations15 May 2019 Hua Wang, Jie Wang, Zhaoxia Yin

Deep Neural Networks (DNNs) are vulnerable to adversarial examples generated by imposing subtle perturbations to inputs that lead a model to predict incorrect outputs.

General Classification Image Classification +1

Theme-aware generation model for chinese lyrics

no code implementations23 May 2019 Jie Wang, Xinyan Zhao

With rapid development of neural networks, deep-learning has been extended to various natural language generation fields, such as machine translation, dialogue generation and even literature creation.

Dialogue Generation Machine Translation +1

Deep learning based mood tagging for Chinese song lyrics

no code implementations23 May 2019 Jie Wang, Yilin Yang

Nowadays, listening music has been and will always be an indispensable part of our daily life.

BIG-bench Machine Learning Information Retrieval +3

A Hierarchical Attention Based Seq2seq Model for Chinese Lyrics Generation

no code implementations15 Jun 2019 Haoshen Fan, Jie Wang, Bojin Zhuang, Shaojun Wang, Jing Xiao

In this paper, we comprehensively study on context-aware generation of Chinese song lyrics.

Sentence

A Syllable-Structured, Contextually-Based Conditionally Generation of Chinese Lyrics

no code implementations15 Jun 2019 Xu Lu, Jie Wang, Bojin Zhuang, Shaojun Wang, Jing Xiao

This paper presents a novel, syllable-structured Chinese lyrics generation model given a piece of original melody.

Automatic Acrostic Couplet Generation with Three-Stage Neural Network Pipelines

no code implementations15 Jun 2019 Haoshen Fan, Jie Wang, Bojin Zhuang, Shaojun Wang, Jing Xiao

In this paper, we comprehensively study on automatic generation of acrostic couplet with the first characters defined by users.

Cultural Vocal Bursts Intensity Prediction Re-Ranking

Cross-Platform Modeling of Users' Behavior on Social Media

no code implementations23 Jun 2019 Haiqian Gu, Jie Wang, Ziwen Wang, Bojin Zhuang, Wenhao Bian, Fei Su

Structured and unstructured data of same users shared by NetEase Music and Sina Weibo have been collected for cross-platform analysis of correlations between music preference and other users' characteristics.

Analyzing Linguistic Complexity and Scientific Impact

no code implementations27 Jul 2019 Chao Lu, Yi Bu, Xianlei Dong, Jie Wang, Ying Ding, Vincent Larivière, Cassidy R. Sugimoto, Logan Paul, Chengzhi Zhang

In this context, scientific writing increasingly plays an important role in scholars' scientific careers.

Generating an Overview Report over Many Documents

no code implementations17 Aug 2019 Jingwen Wang, Hao Zhang, Cheng Zhang, Wenjing Yang, Liqun Shao, Jie Wang

To overcome this obstacle, we present NDORGS (Numerous Documents' Overview Report Generation Scheme) that integrates text filtering, keyword scoring, single-document summarization (SDS), topic modeling, MDS, and title generation to generate a coherent, well-structured ORPT.

Attribute Decision Making +2

Reversible Adversarial Attack based on Reversible Image Transformation

no code implementations6 Nov 2019 Zhaoxia Yin, Hua Wang, Li Chen, Jie Wang, Weiming Zhang

In order to prevent illegal or unauthorized access of image data such as human faces and ensure legitimate users can use authorization-protected data, reversible adversarial attack technique is rise.

Adversarial Attack Image Restoration

D-SPIDER-SFO: A Decentralized Optimization Algorithm with Faster Convergence Rate for Nonconvex Problems

no code implementations28 Nov 2019 Taoxing Pan, Jun Liu, Jie Wang

To the best of our knowledge, D-SPIDER-SFO achieves the state-of-the-art performance for solving nonconvex optimization problems on decentralized networks in terms of the computational cost.

Baryon acoustic oscillations reconstruction using convolutional neural networks

no code implementations24 Feb 2020 Tian-Xiang Mao, Jie Wang, Baojiu Li, Yan-Chuan Cai, Bridget Falck, Mark Neyrinck, Alex Szalay

We propose a new scheme to reconstruct the baryon acoustic oscillations (BAO) signal, which contains key cosmological information, based on deep convolutional neural networks (CNN).

Review of Text Style Transfer Based on Deep Learning

no code implementations6 May 2020 Xiang-Yang Li, Guo Pu, Keyu Ming, Pu Li, Jie Wang, Yuxuan Wang

In the traditional text style transfer model, the text style is generally relied on by experts knowledge and hand-designed rules, but with the application of deep learning in the field of natural language processing, the text style transfer method based on deep learning Started to be heavily researched.

Style Transfer Text Style Transfer

An Unsupervised Semantic Sentence Ranking Scheme for Text Documents

no code implementations28 Apr 2020 Hao Zhang, Jie Wang

It applies two variants of article-structure-biased PageRank to score phrases and words on the first graph and sentences on the second graph.

Clustering Sentence

The simpler the better: vanilla sgd revisited

no code implementations1 Jan 2021 Yueyao Yu, Jie Wang, Wenye Li, Yin Zhang

The stochastic gradient descent (SGD) method, first proposed in 1950's, has been the foundation for deep-neural-network (DNN) training with numerous enhancements including adding a momentum or adaptively selecting learning rates, or using both strategies and more.

Image Classification speech-recognition +1

Meta Sequence Learning for Generating Adequate Question-Answer Pairs

no code implementations4 Oct 2020 Cheng Zhang, Jie Wang

Creating multiple-choice questions to assess reading comprehension of a given article involves generating question-answer pairs (QAPs) on the main points of the document.

Multiple-choice named-entity-recognition +6

Two-sample Test using Projected Wasserstein Distance: Breaking the Curse of Dimensionality

no code implementations22 Oct 2020 Jie Wang, Rui Gao, Yao Xie

We develop a projected Wasserstein distance for the two-sample test, a fundamental problem in statistics and machine learning: given two sets of samples, to determine whether they are from the same distribution.

Generating Adequate Distractors for Multiple-Choice Questions

no code implementations23 Oct 2020 Cheng Zhang, Yicheng Sun, Hejia Chen, Jie Wang

This paper presents a novel approach to automatic generation of adequate distractors for a given question-answer pair (QAP) generated from a given article to form an adequate multiple-choice question (MCQ).

Multiple-choice Part-Of-Speech Tagging +2

Extracting Body Text from Academic PDF Documents for Text Mining

no code implementations23 Oct 2020 Changfeng Yu, Cheng Zhang, Jie Wang

Accurate extraction of body text from PDF-formatted academic documents is essential in text-mining applications for deeper semantic understandings.

Sentence

Reliable Off-policy Evaluation for Reinforcement Learning

no code implementations8 Nov 2020 Jie Wang, Rui Gao, Hongyuan Zha

In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy using logged trajectory data generated from a different behavior policy, without execution of the target policy.

Decision Making Off-policy evaluation +1

Promoting Stochasticity for Expressive Policies via a Simple and Efficient Regularization Method

no code implementations NeurIPS 2020 Qi Zhou, Yufei Kuang, Zherui Qiu, Houqiang Li, Jie Wang

However, in continuous action spaces, integrating entropy regularization with expressive policies is challenging and usually requires complex inference procedures.

Continuous Control reinforcement-learning +1

Topological charge engineering in lasing bound states in continuum

no code implementations31 Dec 2020 Sughra Mohamed, Jie Wang, Heikki Rekola, Janne Heikkinen, Benjamin Asamoah, Lei Shi, Tommi K. Hakala

We experimentally analyze all four observed lasing BICs by imaging their far-field polarization vortices and their associated topological charges.

Optics

Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization

no code implementations ICML Workshop AML 2021 Jie Wang, Zhaoxia Yin, Jing Jiang, Yang Du

In this paper, we propose an attention-guided black-box adversarial attack based on the large-scale multiobjective evolutionary optimization, termed as LMOA.

Adversarial Attack

PICA: A Pixel Correlation-based Attentional Black-box Adversarial Attack

no code implementations19 Jan 2021 Jie Wang, Zhaoxia Yin, Jin Tang, Jing Jiang, Bin Luo

The studies on black-box adversarial attacks have become increasingly prevalent due to the intractable acquisition of the structural knowledge of deep neural networks (DNNs).

Adversarial Attack

UNIT: Unifying Tensorized Instruction Compilation

no code implementations21 Jan 2021 Jian Weng, Animesh Jain, Jie Wang, Leyuan Wang, Yida Wang, Tony Nowatzki

However, it is hard to leverage mixed precision without hardware support because of the overhead of data casting.

Deep Deterministic Policy Gradient for Relay Selection and Power Allocation in Cooperative Communication Network

no code implementations11 Dec 2020 Yuanzhe Geng, Erwu Liu, Rui Wang, Yiming Liu, Jie Wang, Gang Shen, Zhao Dong

Perfect channel state information (CSI) is usually required when considering relay selection and power allocation in cooperative communication.

Information Theory Systems and Control Systems and Control Information Theory

Analysing Wideband Absorbance Immittance in Normal and Ears with Otitis Media with Effusion Using Machine Learning

no code implementations4 Mar 2021 Emad M. Grais, Xiaoya Wang, Jie Wang, Fei Zhao, Wen Jiang, Yuexin Cai, Lifang Zhang, Qingwen Lin, Haidi Yang

Wideband Absorbance Immittance (WAI) has been available for more than a decade, however its clinical use still faces the challenges of limited understanding and poor interpretation of WAI results.

BIG-bench Machine Learning

Adversarially learning disentangled speech representations for robust multi-factor voice conversion

no code implementations30 Jan 2021 Jie Wang, Jingbei Li, Xintao Zhao, Zhiyong Wu, Shiyin Kang, Helen Meng

To increase the robustness of highly controllable style transfer on multiple factors in VC, we propose a disentangled speech representation learning framework based on adversarial learning.

Representation Learning Style Transfer +1

Learning to Optimize Industry-Scale Dynamic Pickup and Delivery Problems

no code implementations27 May 2021 Xijun Li, Weilin Luo, Mingxuan Yuan, Jun Wang, Jiawen Lu, Jie Wang, Jinhu Lu, Jia Zeng

Our method is entirely data driven and thus adaptive, i. e., the relational representation of adjacent vehicles can be learned and corrected by ST-DDGN from data periodically.

Graph Embedding Management +1

Technical Report of Team GraphMIRAcles in the WikiKG90M-LSC Track of OGB-LSC @ KDD Cup 2021

no code implementations12 Jul 2021 Jianyu Cai, Jiajun Chen, Taoxing Pan, Zhanqiu Zhang, Jie Wang

To address this challenge, we propose a framework that integrates three components -- a basic model ComplEx-CMRC, a rule miner AMIE 3, and an inference model to predict missing links.

Knowledge Distillation Knowledge Graphs +1

A 60-GHz Radar Sensor for Micron-Scale Motion Detection

no code implementations23 Jul 2021 Marcel Balle, Chengkai Zhu, Bin Zhang, Jie Wang, Lixin Ran

A compact, continuous-wave, mmWave radar sensor is developed for non-contact detection of micron-scale motions.

Contact Detection Motion Detection

XMUSPEECH System for VoxCeleb Speaker Recognition Challenge 2021

no code implementations6 Sep 2021 Jie Wang, Fuchuang Tong, Zhicong Chen, Lin Li, Qingyang Hong, Haodong Zhou

This paper describes the XMUSPEECH speaker recognition and diarisation systems for the VoxCeleb Speaker Recognition Challenge 2021.

Speaker Recognition

Multi-Modal Multi-Instance Learning for Retinal Disease Recognition

no code implementations25 Sep 2021 Xirong Li, Yang Zhou, Jie Wang, Hailan Lin, Jianchun Zhao, Dayong Ding, Weihong Yu, Youxin Chen

We propose in this paper Multi-Modal Multi-Instance Learning (MM-MIL) for selectively fusing CFP and OCT modalities.

Jointly Learning Agent and Lane Information for Multimodal Trajectory Prediction

no code implementations26 Nov 2021 Jie Wang, Caili Guo, Minan Guo, Jiujiu Chen

JAL-MTP use a Social to Lane (S2L) module to jointly represent the static lane and the dynamic motion of the neighboring agents as instance-level lane, a Recurrent Lane Attention (RLA) mechanism for utilizing the instance-level lanes to predict the map-adaptive future trajectories and two selectors to identify the typical and reasonable trajectories.

Autonomous Vehicles Trajectory Prediction

PAPooling: Graph-based Position Adaptive Aggregation of Local Geometry in Point Clouds

no code implementations28 Nov 2021 Jie Wang, Jianan Li, Lihe Ding, Ying Wang, Tingfa Xu

Fine-grained geometry, captured by aggregation of point features in local regions, is crucial for object recognition and scene understanding in point clouds.

3D Shape Classification graph construction +4

Learning Robust Policy against Disturbance in Transition Dynamics via State-Conservative Policy Optimization

no code implementations20 Dec 2021 Yufei Kuang, Miao Lu, Jie Wang, Qi Zhou, Bin Li, Houqiang Li

Many existing algorithms learn robust policies by modeling the disturbance and applying it to source environments during training, which usually requires prior knowledge about the disturbance and control of simulators.

Fooling the Eyes of Autonomous Vehicles: Robust Physical Adversarial Examples Against Traffic Sign Recognition Systems

no code implementations17 Jan 2022 Wei Jia, Zhaojun Lu, Haichun Zhang, Zhenglin Liu, Jie Wang, Gang Qu

From the view of object detectors, the traffic sign`s position and quality of the video are continuously changing, rendering the digital AEs ineffective in the physical world.

Object Traffic Sign Recognition

Learning to Reformulate for Linear Programming

no code implementations17 Jan 2022 Xijun Li, Qingyu Qu, Fangzhou Zhu, Jia Zeng, Mingxuan Yuan, Kun Mao, Jie Wang

In the past decades, a serial of traditional operation research algorithms have been proposed to obtain the optimum of a given LP in a fewer solving time.

A Data-Driven Approach to Robust Hypothesis Testing Using Sinkhorn Uncertainty Sets

no code implementations9 Feb 2022 Jie Wang, Yao Xie

Hypothesis testing for small-sample scenarios is a practically important problem.

A Survey of Neural Trojan Attacks and Defenses in Deep Learning

no code implementations15 Feb 2022 Jie Wang, Ghulam Mubashar Hassan, Naveed Akhtar

It provides a comprehensible gateway to the broader community to understand the recent developments in Neural Trojans.

Boilerplate Detection via Semantic Classification of TextBlocks

no code implementations9 Mar 2022 Hao Zhang, Jie Wang

We present a hierarchical neural network model called SemText to detect HTML boilerplate based on a novel semantic representation of HTML tags, class names, and text blocks.

Classification

Contextual Networks and Unsupervised Ranking of Sentences

no code implementations9 Mar 2022 Hao Zhang, You Zhou, Jie Wang

We construct a contextual network to represent a document with syntactic and semantic relations between word-sentence pairs, based on which we devise an unsupervised algorithm called CNATAR (Contextual Network And Text Analysis Rank) to score sentences, and rank them through a bi-objective 0-1 knapsack maximization problem over topic analysis and sentence scores.

Sentence

Duality-Induced Regularizer for Semantic Matching Knowledge Graph Embeddings

no code implementations24 Mar 2022 Jie Wang, Zhanqiu Zhang, Zhihao Shi, Jianyu Cai, Shuiwang Ji, Feng Wu

Semantic matching models -- which assume that entities with similar semantics have similar embeddings -- have shown great power in knowledge graph embeddings (KGE).

Entity Embeddings Knowledge Graph Embeddings +1

C3-STISR: Scene Text Image Super-resolution with Triple Clues

no code implementations29 Apr 2022 Minyi Zhao, Miao Wang, Fan Bai, Bingjia Li, Jie Wang, Shuigeng Zhou

In this paper, we present a novel method C3-STISR that jointly exploits the recognizer's feedback, visual and linguistical information as clues to guide super-resolution.

Image Super-Resolution Language Modelling +1

A Manifold Two-Sample Test Study: Integral Probability Metric with Neural Networks

no code implementations4 May 2022 Jie Wang, Minshuo Chen, Tuo Zhao, Wenjing Liao, Yao Xie

Based on the approximation theory of neural networks, we show that the neural network IPM test has the type-II risk in the order of $n^{-(s+\beta)/d}$, which is in the same order of the type-II risk as the H\"older IPM test.

TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback

no code implementations13 Jun 2022 Jie Wang, Fajie Yuan, Mingyue Cheng, Joemon M. Jose, Chenyun Yu, Beibei Kong, Xiangnan He, Zhijin Wang, Bo Hu, Zang Li

That is, the users and the interacted items are represented by their unique IDs, which are generally not shareable across different systems or platforms.

Recommendation Systems Transfer Learning

Exploiting Global Semantic Similarities in Knowledge Graphs by Relational Prototype Entities

no code implementations16 Jun 2022 Xueliang Wang, Jiajun Chen, Feng Wu, Jie Wang

By enforcing the entities' embeddings close to their associated prototypes' embeddings, our approach can effectively encourage the global semantic similarities of entities -- that can be far away in the KG -- connected by the same relation.

Entity Alignment Knowledge Graphs +1

Self-Adaptive Label Augmentation for Semi-supervised Few-shot Classification

no code implementations16 Jun 2022 Xueliang Wang, Jianyu Cai, Shuiwang Ji, Houqiang Li, Feng Wu, Jie Wang

A major novelty of SALA is the task-adaptive metric, which can learn the metric adaptively for different tasks in an end-to-end fashion.

Classification

Flow Rate Independent Multiscale Liquid Biopsy for Precision Oncology

no code implementations19 Jul 2022 Jing Yan, Jie Wang, Robert Dallmann, Renquan Lu, Jérôme Charmet

Immunoaffinity-based liquid biopsies of circulating tumor cells (CTCs) hold great promise for cancer management, but typically suffer from low throughput, relative complexity and post-processing limitations.

Management Specificity

FusionRCNN: LiDAR-Camera Fusion for Two-stage 3D Object Detection

no code implementations22 Sep 2022 Xinli Xu, Shaocong Dong, Lihe Ding, Jie Wang, Tingfa Xu, Jianan Li

Existing 3D detectors significantly improve the accuracy by adopting a two-stage paradigm which merely relies on LiDAR point clouds for 3D proposal refinement.

3D Object Detection Autonomous Driving +2

Tag-Set-Sequence Learning for Generating Question-Answer Pairs

no code implementations20 Oct 2022 Cheng Zhang, Jie Wang

Transformer-based QG models can generate question-answer pairs (QAPs) with high qualities, but may also generate silly questions for certain texts.

named-entity-recognition Named Entity Recognition +4

LMD: A Learnable Mask Network to Detect Adversarial Examples for Speaker Verification

no code implementations2 Nov 2022 Xing Chen, Jie Wang, Xiao-Lei Zhang, Wei-Qiang Zhang, Kunde Yang

It utilizes score variation as an indicator to detect adversarial examples, where the score variation is the absolute discrepancy between the ASV scores of an original audio recording and its transformed audio synthesized from its masked complex spectrogram.

Speaker Verification

Interpretable Diabetic Retinopathy Diagnosis based on Biomarker Activation Map

no code implementations13 Dec 2022 Pengxiao Zang, Tristan T. Hormel, Jie Wang, Yukun Guo, Steven T. Bailey, Christina J. Flaxel, David Huang, Thomas S. Hwang, Yali Jia

To ensure that the BAM only highlights classifier-utilized biomarkers an assistant generator was trained to do the opposite, producing scans that would be classified as referable by the classifier from non-referable scans.

Decision Making

Efficient Exploration in Resource-Restricted Reinforcement Learning

no code implementations14 Dec 2022 Zhihai Wang, Taoxing Pan, Qi Zhou, Jie Wang

In many real-world applications of reinforcement learning (RL), performing actions requires consuming certain types of resources that are non-replenishable in each episode.

Efficient Exploration reinforcement-learning +1

Two Measure is Two Know: Calibration-free Full Duplex Monitoring for Software Radio Platforms

no code implementations15 Dec 2022 Jie Wang, Jonathan Gornet, Alex Orange, Leigh Stoller, Gary Wong, Jacobus Van der Merwe, Sneha Kumar Kasera, Neal Patwari

FDMonitor thus uses a bidirectional coupler, a two-channel receiver, and a new source separation algorithm to simultaneously estimate the transmitted signal and the signal incident on the antenna.

Vocal Bursts Valence Prediction

Deep learning numerical methods for high-dimensional fully nonlinear PIDEs and coupled FBSDEs with jumps

no code implementations30 Jan 2023 Wansheng Wang, Jie Wang, Jinping Li, Feifei Gao, Yi Fu

We propose a deep learning algorithm for solving high-dimensional parabolic integro-differential equations (PIDEs) and high-dimensional forward-backward stochastic differential equations with jumps (FBSDEJs), where the jump-diffusion process are derived by a Brownian motion and an independent compensated Poisson random measure.

Learning Cut Selection for Mixed-Integer Linear Programming via Hierarchical Sequence Model

no code implementations1 Feb 2023 Zhihai Wang, Xijun Li, Jie Wang, Yufei Kuang, Mingxuan Yuan, Jia Zeng, Yongdong Zhang, Feng Wu

Cut selection -- which aims to select a proper subset of the candidate cuts to improve the efficiency of solving MILPs -- heavily depends on (P1) which cuts should be preferred, and (P2) how many cuts should be selected.

Variable Selection for Kernel Two-Sample Tests

no code implementations15 Feb 2023 Jie Wang, Santanu S. Dey, Yao Xie

We consider the variable selection problem for two-sample tests, aiming to select the most informative variables to distinguish samples from two groups.

Variable Selection Vocal Bursts Valence Prediction

Sparse Bayesian Learning-Based 3D Spectrum Environment Map Construction-Sampling Optimization, Scenario-Dependent Dictionary Construction and Sparse Recovery

no code implementations25 Feb 2023 Jie Wang, Qiuming Zhu, Zhipeng Lin, Qihui Wu, Yang Huang, Xuezhao Cai, Weizhi Zhong, Yi Zhao

Then, a maximum and minimum distance (MMD) clustering-based SBL algorithm is proposed to recover the spectrum data at the unsampled positions and construct the whole 3D SEM.

Management

Provably Convergent Subgraph-wise Sampling for Fast GNN Training

no code implementations17 Mar 2023 Jie Wang, Zhihao Shi, Xize Liang, Shuiwang Ji, Bin Li, Feng Wu

During the message passing (MP) in GNNs, subgraph-wise sampling methods discard messages outside the mini-batches in backward passes to avoid the well-known neighbor explosion problem, i. e., the exponentially increasing dependencies of nodes with the number of MP iterations.

Can LLMs like GPT-4 outperform traditional AI tools in dementia diagnosis? Maybe, but not today

no code implementations2 Jun 2023 Zhuo Wang, Rongzhen Li, Bowen Dong, Jie Wang, Xiuxing Li, Ning Liu, Chenhui Mao, Wei zhang, Liling Dong, Jing Gao, Jianyong Wang

In this paper, we explore the potential of LLMs such as GPT-4 to outperform traditional AI tools in dementia diagnosis.

Community Detection Graph Convolutional Network for Overlap-Aware Speaker Diarization

no code implementations26 Jun 2023 Jie Wang, Zhicong Chen, Haodong Zhou, Lin Li, Qingyang Hong

The CDGCN-based clustering method consists of graph generation, sub-graph detection, and Graph-based Overlapped Speech Detection (Graph-OSD).

Clustering Community Detection +3

HiREN: Towards Higher Supervision Quality for Better Scene Text Image Super-Resolution

no code implementations31 Jul 2023 Minyi Zhao, Yi Xu, Bingjia Li, Jie Wang, Jihong Guan, Shuigeng Zhou

Observing the quality issue of HR images, in this paper we propose a novel idea to boost STISR by first enhancing the quality of HR images and then using the enhanced HR images as supervision to do STISR.

Image Generation Image Super-Resolution

A Novel Ehanced Move Recognition Algorithm Based on Pre-trained Models with Positional Embeddings

no code implementations14 Aug 2023 Hao Wen, Jie Wang, Xiaodong Qiao

The recognition of abstracts is crucial for effectively locating the content and clarifying the article.

Position

Context-Aware Prompt Tuning for Vision-Language Model with Dual-Alignment

no code implementations8 Sep 2023 Hongyu Hu, Tiancheng Lin, Jie Wang, Zhenbang Sun, Yi Xu

To achieve this, we introduce a pre-trained LLM to generate context descriptions, and we encourage the prompts to learn from the LLM's knowledge by alignment, as well as the alignment between prompts and local image features.

Language Modelling Zero-Shot Learning

A Ground Segmentation Method Based on Point Cloud Map for Unstructured Roads

no code implementations15 Sep 2023 Zixuan Li, Haiying Lin, Zhangyu Wang, Huazhi Li, Miao Yu, Jie Wang

Unstructured road scenes represented by open-pit mines have irregular boundary lines and uneven road surfaces, which lead to segmentation errors in current ground segmentation methods.

Point Cloud Registration Segmentation

Can Class-Priors Help Single-Positive Multi-Label Learning?

no code implementations25 Sep 2023 Biao Liu, Jie Wang, Ning Xu, Xin Geng

Single-positive multi-label learning (SPMLL) is a typical weakly supervised multi-label learning problem, where each training example is annotated with only one positive label.

Multi-Label Learning

Serving Deep Learning Model in Relational Databases

no code implementations7 Oct 2023 Alexandre Eichenberger, Qi Lin, Saif Masood, Hong Min, Alexander Sim, Jie Wang, Yida Wang, Kesheng Wu, Binhang Yuan, Lixi Zhou, Jia Zou

Serving deep learning (DL) models on relational data has become a critical requirement across diverse commercial and scientific domains, sparking growing interest recently.

Exploring the relationship between response time sequence in scale answering process and severity of insomnia: a machine learning approach

no code implementations13 Oct 2023 Zhao Su, Rongxun Liu, Keyin Zhou, Xinru Wei, Ning Wang, Zexin Lin, Yuanchen Xie, Jie Wang, Fei Wang, Shenzhong Zhang, Xizhe Zhang

The relationship between symptom severity and response time was explored, and a machine learning model was developed to predict the presence of insomnia.

Accelerate Presolve in Large-Scale Linear Programming via Reinforcement Learning

no code implementations18 Oct 2023 Yufei Kuang, Xijun Li, Jie Wang, Fangzhou Zhu, Meng Lu, Zhihai Wang, Jia Zeng, Houqiang Li, Yongdong Zhang, Feng Wu

Specifically, we formulate the routine design task as a Markov decision process and propose an RL framework with adaptive action sequences to generate high-quality presolve routines efficiently.

reinforcement-learning Reinforcement Learning (RL)

Channel Estimation via Loss Field: Accurate Site-Trained Modeling for Shadowing Prediction

no code implementations18 Oct 2023 Jie Wang, Meles G. Weldegebriel, Neal Patwari

We propose a new channel model, CELF, which uses channel loss measurements from a deployed network in the area and a Bayesian linear regression method to estimate a site-specific loss field for the area.

Promoting Generalization for Exact Solvers via Adversarial Instance Augmentation

no code implementations22 Oct 2023 Haoyang Liu, Yufei Kuang, Jie Wang, Xijun Li, Yongdong Zhang, Feng Wu

To tackle this problem, we propose a novel approach, which is called Adversarial Instance Augmentation and does not require to know the problem type for new instance generation, to promote data diversity for learning-based branching modules in the branch-and-bound (B&B) Solvers (AdaSolver).

Imitation Learning

Affective Video Content Analysis: Decade Review and New Perspectives

no code implementations26 Oct 2023 Junxiao Xue, Jie Wang, Xuecheng Wu, Qian Zhang

In this study, we comprehensively review the development of AVCA over the past decade, particularly focusing on the most advanced methods adopted to address the three major challenges of video feature extraction, expression subjectivity, and multimodal feature fusion.

Emotional Intelligence Facial Expression Recognition +1

Content Significance Distribution of Sub-Text Blocks in Articles and Its Application to Article-Organization Assessment

no code implementations3 Nov 2023 You Zhou, Jie Wang

We explore how to capture the significance of a sub-text block in an article and how it may be used for text mining tasks.

Sentence Sentence Embeddings

Generalizing SDP-Based Barrier Certificate Synthesis to Unbounded Domains by Dropping Archimedean Condition

no code implementations24 Dec 2023 Hao Wu, Shenghua Feng, Ting Gan, Jie Wang, Bican Xia, Naijun Zhan

Barrier certificates, which serve as differential invariants that witness system safety, play a crucial role in the verification of cyber-physical systems (CPS).

Machine Learning Insides OptVerse AI Solver: Design Principles and Applications

no code implementations11 Jan 2024 Xijun Li, Fangzhou Zhu, Hui-Ling Zhen, Weilin Luo, Meng Lu, Yimin Huang, Zhenan Fan, Zirui Zhou, Yufei Kuang, Zhihai Wang, Zijie Geng, Yang Li, Haoyang Liu, Zhiwu An, Muming Yang, Jianshu Li, Jie Wang, Junchi Yan, Defeng Sun, Tao Zhong, Yong Zhang, Jia Zeng, Mingxuan Yuan, Jianye Hao, Jun Yao, Kun Mao

To this end, we present a comprehensive study on the integration of machine learning (ML) techniques into Huawei Cloud's OptVerse AI Solver, which aims to mitigate the scarcity of real-world mathematical programming instances, and to surpass the capabilities of traditional optimization techniques.

Decision Making Management

Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling

no code implementations17 Jan 2024 Hong Wang, Zhongkai Hao, Jie Wang, Zijie Geng, Zhen Wang, Bin Li, Feng Wu

To the best of our knowledge, SKR is the first attempt to address the time-consuming nature of data generation for learning neural operators.

Learning to Stop Cut Generation for Efficient Mixed-Integer Linear Programming

no code implementations31 Jan 2024 Haotian Ling, Zhihai Wang, Jie Wang

A key problem for cuts is when to stop cuts generation, which is important for the efficiency of solving MILPs.

Decision Making

Building Open-Ended Embodied Agent via Language-Policy Bidirectional Adaptation

no code implementations12 Dec 2023 Shaopeng Zhai, Jie Wang, Tianyi Zhang, Fuxian Huang, Qi Zhang, Ming Zhou, Jing Hou, Yu Qiao, Yu Liu

Building embodied agents on integrating Large Language Models (LLMs) and Reinforcement Learning (RL) have revolutionized human-AI interaction: researchers can now leverage language instructions to plan decision-making for open-ended tasks.

Decision Making Language Modelling +1

Accelerating PDE Data Generation via Differential Operator Action in Solution Space

no code implementations4 Feb 2024 Huanshuo Dong, Hong Wang, Haoyang Liu, Jian Luo, Jie Wang

It applies differential operators on these solutions, a process we call 'operator action', to efficiently generate precise PDE data points.

PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design

no code implementations8 Mar 2024 Wenqi Jiang, Shuai Zhang, Boran Han, Jie Wang, Bernie Wang, Tim Kraska

Retrieval-augmented generation (RAG) can enhance the generation quality of large language models (LLMs) by incorporating external token databases.

Retrieval

Non-Convex Robust Hypothesis Testing using Sinkhorn Uncertainty Sets

no code implementations21 Mar 2024 Jie Wang, Rui Gao, Yao Xie

We present a new framework to address the non-convex robust hypothesis testing problem, wherein the goal is to seek the optimal detector that minimizes the maximum of worst-case type-I and type-II risk functions.

Computational Efficiency

Reinforcement Learning-based Recommender Systems with Large Language Models for State Reward and Action Modeling

no code implementations25 Mar 2024 Jie Wang, Alexandros Karatzoglou, Ioannis Arapakis, Joemon M. Jose

The LE is learned from a subset of user-item interaction data, thus reducing the need for large training data, and can synthesise user feedback for offline data by: (i) acting as a state model that produces high quality states that enrich the user representation, and (ii) functioning as a reward model to accurately capture nuanced user preferences on actions.

Offline RL Reinforcement Learning (RL) +1

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