Search Results for author: Wei Ma

Found 40 papers, 14 papers with code

CLIO: Role-interactive Multi-event Head Attention Network for Document-level Event Extraction

no code implementations COLING 2022 Yubing Ren, Yanan Cao, Fang Fang, Ping Guo, Zheng Lin, Wei Ma, Yi Liu

Transforming the large amounts of unstructured text on the Internet into structured event knowledge is a critical, yet unsolved goal of NLP, especially when addressing document-level text.

Document-level Event Extraction Event Extraction

Spatiotemporal Implicit Neural Representation as a Generalized Traffic Data Learner

no code implementations6 May 2024 Tong Nie, Guoyang Qin, Wei Ma, Jian Sun

Spatiotemporal Traffic Data (STTD) measures the complex dynamical behaviors of the multiscale transportation system.

Inductive Bias

Potential Paradigm Shift in Hazard Risk Management: AI-Based Weather Forecast for Tropical Cyclone Hazards

no code implementations29 Apr 2024 Kairui Feng, Dazhi Xi, Wei Ma, Cao Wang, Yuanlong Li, Xuanhong Chen

The advents of Artificial Intelligence (AI)-driven models marks a paradigm shift in risk management strategies for meteorological hazards.


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

Synergizing Spatial Optimization with Large Language Models for Open-Domain Urban Itinerary Planning

no code implementations11 Feb 2024 Yihong Tang, Zhaokai Wang, Ao Qu, Yihao Yan, Kebing Hou, Dingyi Zhuang, Xiaotong Guo, Jinhua Zhao, Zhan Zhao, Wei Ma

In this paper, we for the first time propose the task of Open-domain Urban Itinerary Planning (OUIP) for citywalk, which directly generates itineraries based on users' requests described in natural language.

LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning

no code implementations29 Jan 2024 Yuqiang Sun, Daoyuan Wu, Yue Xue, Han Liu, Wei Ma, Lyuye Zhang, Miaolei Shi, Yang Liu

Large language models (LLMs) have demonstrated significant poten- tial for many downstream tasks, including those requiring human- level intelligence, such as vulnerability detection.

Vulnerability Detection

ImputeFormer: Low Rankness-Induced Transformers for Generalizable Spatiotemporal Imputation

1 code implementation4 Dec 2023 Tong Nie, Guoyang Qin, Wei Ma, Yuewen Mei, Jian Sun

The exploitation of the inherent structures of spatiotemporal data enables our model to learn balanced signal-noise representations, making it versatile for a variety of imputation problems.

Inductive Bias Multivariate Time Series Imputation +1

Normalizing flow-based deep variational Bayesian network for seismic multi-hazards and impacts estimation from InSAR imagery

no code implementations20 Oct 2023 Xuechun Li, Paula M. Burgi, Wei Ma, Hae Young Noh, David J. Wald, Susu Xu

Onsite disasters like earthquakes can trigger cascading hazards and impacts, such as landslides and infrastructure damage, leading to catastrophic losses; thus, rapid and accurate estimates are crucial for timely and effective post-disaster responses.

Variational Inference

Evaluating the Robustness of Test Selection Methods for Deep Neural Networks

no code implementations29 Jul 2023 Qiang Hu, Yuejun Guo, Xiaofei Xie, Maxime Cordy, Wei Ma, Mike Papadakis, Yves Le Traon

Testing deep learning-based systems is crucial but challenging due to the required time and labor for labeling collected raw data.

Fault Detection

The Relationship Between Speech Features Changes When You Get Depressed: Feature Correlations for Improving Speed and Performance of Depression Detection

no code implementations6 Jul 2023 Fuxiang Tao, Wei Ma, Xuri Ge, Anna Esposito, Alessandro Vinciarelli

The results show that the models used in the experiments improve in terms of training speed and performance when fed with feature correlation matrices rather than with feature vectors.

Depression Detection Feature Correlation

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.

A Black-Box Attack on Code Models via Representation Nearest Neighbor Search

no code implementations10 May 2023 Jie Zhang, Wei Ma, Qiang Hu, Shangqing Liu, Xiaofei Xie, Yves Le Traon, Yang Liu

Furthermore, the perturbation of adversarial examples introduced by RNNS is smaller compared to the baselines in terms of the number of replaced variables and the change in variable length.

Adversarial Attack Clone Detection

Beyond Prediction: On-street Parking Recommendation using Heterogeneous Graph-based List-wise Ranking

1 code implementation29 Apr 2023 Hanyu Sun, Xiao Huang, Wei Ma

In this paper, we first time propose an on-street parking recommendation (OPR) task to directly recommend a parking space for a driver.

Computational Efficiency

Maximin Headway Control of Automated Vehicles for System Optimal Dynamic Traffic Assignment in General Networks

no code implementations29 Mar 2023 Jinxiao Du, Wei Ma

Specifically, we aim to search for the optimal time headway between AVs on each link that achieves the network-wide system optimal dynamic traffic assignment (SO-DTA).

Demonstration-guided Deep Reinforcement Learning for Coordinated Ramp Metering and Perimeter Control in Large Scale Networks

no code implementations4 Mar 2023 Zijian Hu, Wei Ma

This study considers two representative control approaches: ramp metering for freeways and perimeter control for homogeneous urban roads, and we aim to develop a deep reinforcement learning (DRL)-based coordinated control framework for large-scale networks.

Myopia prediction for adolescents via time-aware deep learning

no code implementations26 Sep 2022 Junjia Huang, Wei Ma, Rong Li, Na Zhao, Tao Zhou

Result: The mean absolute prediction error on the testing set was 0. 273-0. 257 for spherical equivalent, ranging from 0. 189-0. 160 to 0. 596-0. 473 if we consider different lengths of historical records and different prediction durations.

Time Series Time Series Analysis

Estimating probabilistic dynamic origin-destination demands using multi-day traffic data on computational graphs

no code implementations20 Apr 2022 Wei Ma, Sean Qian

The proposed framework is cast into the computational graph and a reparametrization trick is developed to estimate the mean and standard deviation of the probabilistic dynamic OD demand simultaneously.

Decision Making

Few-Sample Traffic Prediction with Graph Networks using Locale as Relational Inductive Biases

1 code implementation8 Mar 2022 Mingxi Li, Yihong Tang, Wei Ma

Currently, most of the state-of-the-art prediction models are based on graph neural networks (GNNs), and the required training samples are proportional to the size of the traffic network.

Management Open-Ended Question Answering +1

Attacking Deep Reinforcement Learning-Based Traffic Signal Control Systems with Colluding Vehicles

no code implementations4 Nov 2021 Ao Qu, Yihong Tang, Wei Ma

In view of this, this paper first time formulates a novel task in which a group of vehicles can cooperatively send falsified information to "cheat" DRL-based ATCS in order to save their total travel time.

reinforcement-learning Reinforcement Learning (RL)

Network-wide link travel time and station waiting time estimation using automatic fare collection data: A computational graph approach

no code implementations19 Aug 2021 Jinlei Zhang, Feng Chen, Lixing Yang, Wei Ma, Guangyin Jin, Ziyou Gao

This paper focuses on an essential and hard problem to estimate the network-wide link travel time and station waiting time using the automatic fare collection (AFC) data in the URT system, which is beneficial to better understand the system-wide real-time operation state.

Adversarial Diffusion Attacks on Graph-based Traffic Prediction Models

1 code implementation19 Apr 2021 Lyuyi Zhu, Kairui Feng, Ziyuan Pu, Wei Ma

The diffusion attack aims to select and attack a small set of nodes to degrade the performance of the entire prediction model.

Adversarial Attack Management +1

Line Flow based SLAM

no code implementations21 Sep 2020 Qiuyuan Wang, Zike Yan, Junqiu Wang, Fei Xue, Wei Ma, Hongbin Zha

To address these problems, we leverage a line flow to encode the coherence of line segment observations of the same 3D line along the temporal dimension, which has been neglected in prior SLAM systems.

Short-term origin-destination demand prediction in urban rail transit systems: A channel-wise attentive split-convolutional neural network method

no code implementations8 Aug 2020 Jinlei Zhang, Hongshu Che, Feng Chen, Wei Ma, Zhengbing He

The proposed model contributes to the development of short-term OD flow prediction, and it also lays the foundations of real-time URT operation and management.

Benchmarking Management

Missing Not at Random in Matrix Completion: The Effectiveness of Estimating Missingness Probabilities Under a Low Nuclear Norm Assumption

1 code implementation NeurIPS 2019 Wei Ma, George H. Chen

Recently, various papers have shown that we can reduce this bias in MNAR matrix completion if we know the probabilities of different matrix entries being missing.

Matrix Completion regression

High-Resolution Traffic Sensing with Autonomous Vehicles

1 code implementation6 Oct 2019 Wei Ma, Sean Qian

The last decades have witnessed the breakthrough of autonomous vehicles (AVs), and the perception capabilities of AVs have been dramatically improved.

Autonomous Vehicles Management +1

Test Selection for Deep Learning Systems

no code implementations30 Apr 2019 Wei Ma, Mike Papadakis, Anestis Tsakmalis, Maxime Cordy, Yves Le Traon

This raises the question of how we can automatically select candidate test data to test deep learning models.

General Classification Image Classification

Estimating multi-class dynamic origin-destination demand through a forward-backward algorithm on computational graphs

no code implementations12 Mar 2019 Wei Ma, Xidong Pi, Sean Qian

Provided with some observations of vehicular flow for each class in a large-scale transportation network, how to estimate the multi-class spatio-temporal vehicular flow, in terms of time-varying Origin-Destination (OD) demand and path/link flow, remains a big challenge.

Probabilistic representation and inverse design of metamaterials based on a deep generative model with semi-supervised learning strategy

2 code implementations30 Jan 2019 Wei Ma, Feng Cheng, Yihao Xu, Qinlong Wen, Yongmin Liu

To better unveil this implicit relationship and thus facilitate metamaterial design, we propose to represent metamaterials and model the inverse design problem in a probabilistically generative manner.


Estimating multi-year 24/7 origin-destination demand using high-granular multi-source traffic data

1 code implementation26 Jan 2019 Wei Ma, Zhen, Qian

A GPU-based stochastic projected gradient descent method is proposed to efficiently solve the multi-year 24/7 DODE problem.

Traffic Prediction

A deep learning approach to real-time parking occupancy prediction in spatio-temporal networks incorporating multiple spatio-temporal data sources

1 code implementation21 Jan 2019 Shuguan Yang, Wei Ma, Xidong Pi, Sean Qian

The case study also shows that, in generally, the prediction model works better for business areas than for recreational locations.

Efficient Traffic-Sign Recognition with Scale-aware CNN

no code implementations31 May 2018 Yuchen Yang, Shuo Liu, Wei Ma, Qiuyuan Wang, Zheng Liu

The paper presents a Traffic Sign Recognition (TSR) system, which can fast and accurately recognize traffic signs of different sizes in images.

General Classification Traffic Sign Recognition

CompNet: Neural networks growing via the compact network morphism

no code implementations27 Apr 2018 Jun Lu, Wei Ma, Boi Faltings

We explored $CompNet$, in which case we morph a well-trained neural network to a deeper one where network function can be preserved and the added layer is compact.


An Equivalence of Fully Connected Layer and Convolutional Layer

1 code implementation4 Dec 2017 Wei Ma, Jun Lu

The article is helpful for the beginners of the neural network to understand how fully connected layer and the convolutional layer work in the backend.

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