Search Results for author: Shuai Ma

Found 38 papers, 8 papers with code

Charting the Future of AI in Project-Based Learning: A Co-Design Exploration with Students

no code implementations26 Jan 2024 Chengbo Zheng, Kangyu Yuan, Bingcan Guo, Reza Hadi Mogavi, Zhenhui Peng, Shuai Ma, Xiaojuan Ma

The increasing use of Artificial Intelligence (AI) by students in learning presents new challenges for assessing their learning outcomes in project-based learning (PBL).

Voila-A: Aligning Vision-Language Models with User's Gaze Attention

no code implementations22 Dec 2023 Kun Yan, Lei Ji, Zeyu Wang, Yuntao Wang, Nan Duan, Shuai Ma

In this paper, we introduce gaze information, feasibly collected by AR or VR devices, as a proxy for human attention to guide VLMs and propose a novel approach, Voila-A, for gaze alignment to enhance the interpretability and effectiveness of these models in real-world applications.

Feasibility Conditions for Mobile LiFi

no code implementations20 Dec 2023 Shuai Ma, Haihong Sheng, Junchang Sun, Hang Li, Xiaodong Liu, Chen Qiu, Majid Safari, Naofal Al-Dhahir, Shiyin Li

Then, we derive the expression of LiFi transmission rate based on the m-pulse-amplitude-modulation (M-PAM).

MATA*: Combining Learnable Node Matching with A* Algorithm for Approximate Graph Edit Distance Computation

no code implementations4 Nov 2023 Junfeng Liu, Min Zhou, Shuai Ma, Lujia Pan

Graph Edit Distance (GED) is a general and domain-agnostic metric to measure graph similarity, widely used in graph search or retrieving tasks.

Graph Similarity

Joint Beamforming Design for RIS-enabled Integrated Positioning and Communication in Millimeter Wave Systems

no code implementations20 May 2023 Junchang Sun, Shuai Ma, Shiyin Li

Integrated positioning and communication (IPAC) system and reconfigurable intelligent surface (RIS) are both considered to be key technologies for future wireless networks.

Robust Power Allocation for UAV-aided ISAC Systems with Uncertain Location Sensing Errors

no code implementations8 May 2023 Junchang Sun, Shuai Ma, Ruixin Yang, Yang Tingting, Shiyin Li

Unmanned aerial vehicle (UAV) holds immense potential in integrated sensing and communication (ISAC) systems for the Internet of Things (IoT).

Robust Design

Mathematical Characterization of Signal Semantics and Rethinking of the Mathematical Theory of Information

no code implementations26 Mar 2023 Guangming Shi, Dahua Gao, Shuai Ma, Minxi Yang, Yong Xiao, Xuemei Xie

Shannon information theory is established based on probability and bits, and the communication technology based on this theory realizes the information age.

Features Disentangled Semantic Broadcast Communication Networks

no code implementations3 Mar 2023 Shuai Ma, Weining Qiao, Youlong Wu, Hang Li, Guangming Shi, Dahua Gao, Yuanming Shi, Shiyin Li, Naofal Al-Dhahir

Instead of broadcasting all extracted features, the semantic encoder extracts the disentangled semantic features, and then only the users' intended semantic features are selected for broadcasting, which can further improve the transmission efficiency.

feature selection

Task-oriented Explainable Semantic Communications

no code implementations27 Feb 2023 Shuai Ma, Weining Qiao, Youlong Wu, Hang Li, Guangming Shi, Dahua Gao, Yuanming Shi, Shiyin Li, Naofal Al-Dhahir

Furthermore, based on the $\beta $-variational autoencoder ($\beta $-VAE), we propose a practical explainable semantic communication system design, which simultaneously achieves semantic features selection and is robust against semantic channel noise.

Global Algorithms for Mean-Variance Optimization in Markov Decision Processes

no code implementations27 Feb 2023 Li Xia, Shuai Ma

In this paper, we propose a new approach to find the globally optimal policy for combined metrics of steady-state mean and variance in an infinite-horizon undiscounted MDP.


Competent but Rigid: Identifying the Gap in Empowering AI to Participate Equally in Group Decision-Making

no code implementations17 Feb 2023 Chengbo Zheng, Yuheng Wu, Chuhan Shi, Shuai Ma, Jiehui Luo, Xiaojuan Ma

Existing research on human-AI collaborative decision-making focuses mainly on the interaction between AI and individual decision-makers.

Decision Making

Joint Beamforming and PD Orientation Design for Mobile Visible Light Communications

no code implementations21 Dec 2022 Shuai Ma, Jing Wang, Chun Du, Hang Li, Xiaodong Liu, Youlong Wu, Naofal Al-Dhahir, Shiyin Li

To address this challenge, we propose an alternating optimization algorithm to obtain the transmit beamforming and the PD orientation.

HORIZON: High-Resolution Semantically Controlled Panorama Synthesis

no code implementations10 Oct 2022 Kun Yan, Lei Ji, Chenfei Wu, Jian Liang, Ming Zhou, Nan Duan, Shuai Ma

Panorama synthesis endeavors to craft captivating 360-degree visual landscapes, immersing users in the heart of virtual worlds.

Vocal Bursts Intensity Prediction

Robust Information Bottleneck for Task-Oriented Communication with Digital Modulation

1 code implementation21 Sep 2022 Songjie Xie, Shuai Ma, Ming Ding, Yuanming Shi, Mingjian Tang, Youlong Wu

Task-oriented communications, mostly using learning-based joint source-channel coding (JSCC), aim to design a communication-efficient edge inference system by transmitting task-relevant information to the receiver.


Self-supervised Learning for Heterogeneous Graph via Structure Information based on Metapath

no code implementations9 Sep 2022 Shuai Ma, Jian-wei Liu, Xin Zuo

Empirical results validate the performance of SESIM method and demonstrate that this method can improve the representation ability of traditional neural networks on link prediction task and node classification task.

Link Prediction Meta-Learning +3

Ered: Enhanced Text Representations with Entities and Descriptions

1 code implementation18 Aug 2022 Qinghua Zhao, Shuai Ma, Yuxuan Lei

On the one hand, it is implicit and only model weights are paid attention to, the pre-trained entity embeddings are ignored.

Entity Embeddings

Mean-Semivariance Policy Optimization via Risk-Averse Reinforcement Learning

no code implementations15 Jun 2022 Xiaoteng Ma, Shuai Ma, Li Xia, Qianchuan Zhao

Keeping risk under control is often more crucial than maximizing expected rewards in real-world decision-making situations, such as finance, robotics, autonomous driving, etc.

Autonomous Driving Continuous Control +3

TraceNet: Tracing and Locating the Key Elements in Sentiment Analysis

1 code implementation28 Feb 2022 Qinghua Zhao, Shuai Ma

In this paper, we study sentiment analysis task where the outcomes are mainly contributed by a few key elements of the inputs.

Sentiment Analysis Sentiment Classification

KESA: A Knowledge Enhanced Approach For Sentiment Analysis

1 code implementation24 Feb 2022 Qinghua Zhao, Shuai Ma, Shuo Ren

On the contrary, the second task predicts the overall sentiment polarity given the sentiment polarity of the word as prior knowledge.

Sentence Sentiment Analysis

A unified algorithm framework for mean-variance optimization in discounted Markov decision processes

no code implementations15 Jan 2022 Shuai Ma, Xiaoteng Ma, Li Xia

To deal with this unorthodox problem, we introduce a pseudo mean to transform the untreatable MDP to a standard one with a redefined reward function in standard form and derive a discounted mean-variance performance difference formula.

Bilevel Optimization Management

SemFace: Pre-training Encoder and Decoder with a Semantic Interface for Neural Machine Translation

no code implementations ACL 2021 Shuo Ren, Long Zhou, Shujie Liu, Furu Wei, Ming Zhou, Shuai Ma

While pre-training techniques are working very well in natural language processing, how to pre-train a decoder and effectively use it for neural machine translation (NMT) still remains a tricky issue.

Machine Translation NMT +1

Control Image Captioning Spatially and Temporally

no code implementations ACL 2021 Kun Yan, Lei Ji, Huaishao Luo, Ming Zhou, Nan Duan, Shuai Ma

Moreover, the controllability and explainability of LoopCAG are validated by analyzing spatial and temporal sensitivity during the generation process.

Contrastive Learning Image Captioning +1

SceneRec: Scene-Based Graph Neural Networks for Recommender Systems

no code implementations12 Feb 2021 Gang Wang, Ziyi Guo, Xiang Li, Dawei Yin, Shuai Ma

Collaborative filtering has been largely used to advance modern recommender systems to predict user preference.

Collaborative Filtering Recommendation Systems +1

CASS: Towards Building a Social-Support Chatbot for Online Health Community

2 code implementations4 Jan 2021 Liuping Wang, Dakuo Wang, Feng Tian, Zhenhui Peng, Xiangmin Fan, Zhan Zhang, Shuai Ma, Mo Yu, Xiaojuan Ma, Hongan Wang

Chatbots systems, despite their popularity in today's HCI and CSCW research, fall short for one of the two reasons: 1) many of the systems use a rule-based dialog flow, thus they can only respond to a limited number of pre-defined inputs with pre-scripted responses; or 2) they are designed with a focus on single-user scenarios, thus it is unclear how these systems may affect other users or the community.


CodeBLEU: a Method for Automatic Evaluation of Code Synthesis

2 code implementations22 Sep 2020 Shuo Ren, Daya Guo, Shuai Lu, Long Zhou, Shujie Liu, Duyu Tang, Neel Sundaresan, Ming Zhou, Ambrosio Blanco, Shuai Ma

Evaluation metrics play a vital role in the growth of an area as it defines the standard of distinguishing between good and bad models.

Code Translation Translation

A Retrieve-and-Rewrite Initialization Method for Unsupervised Machine Translation

1 code implementation ACL 2020 Shuo Ren, Yu Wu, Shujie Liu, Ming Zhou, Shuai Ma

The commonly used framework for unsupervised machine translation builds initial translation models of both translation directions, and then performs iterative back-translation to jointly boost their translation performance.

NMT Retrieval +3

Explicit Cross-lingual Pre-training for Unsupervised Machine Translation

no code implementations IJCNLP 2019 Shuo Ren, Yu Wu, Shujie Liu, Ming Zhou, Shuai Ma

Pre-training has proven to be effective in unsupervised machine translation due to its ability to model deep context information in cross-lingual scenarios.

Language Modelling Translation +1

Variance-Based Risk Estimations in Markov Processes via Transformation with State Lumping

no code implementations9 Jul 2019 Shuai Ma, Jia Yuan Yu

In the numerical experiment, we illustrate state lumping in the SAT, errors from a naive reward simplification, and the validity of the SAT for the two risk estimations.

Reinforcement Learning (RL)

A Scheme for Dynamic Risk-Sensitive Sequential Decision Making

no code implementations9 Jul 2019 Shuai Ma, Jia Yuan Yu, Ahmet Satir

For a given risk-sensitive problem, in which the objective and constraints are, or can be estimated by, functions of the mean and variance of return, we generate a synthetic dataset as training data.

Decision Making

Deep Learning for Signal Demodulation in Physical Layer Wireless Communications: Prototype Platform, Open Dataset, and Analytics

no code implementations8 Mar 2019 Hongmei Wang, Zhenzhen Wu, Shuai Ma, Songtao Lu, Han Zhang, Guoru Ding, Shiyin Li

In this paper, we investigate deep learning (DL)-enabled signal demodulation methods and establish the first open dataset of real modulated signals for wireless communication systems.

Unsupervised Neural Machine Translation with SMT as Posterior Regularization

1 code implementation14 Jan 2019 Shuo Ren, Zhirui Zhang, Shujie Liu, Ming Zhou, Shuai Ma

To address this issue, we introduce phrase based Statistic Machine Translation (SMT) models which are robust to noisy data, as posterior regularizations to guide the training of unsupervised NMT models in the iterative back-translation process.

NMT Translation +1

Triangular Architecture for Rare Language Translation

no code implementations ACL 2018 Shuo Ren, Wenhu Chen, Shujie Liu, Mu Li, Ming Zhou, Shuai Ma

Neural Machine Translation (NMT) performs poor on the low-resource language pair $(X, Z)$, especially when $Z$ is a rare language.

Machine Translation NMT +1

State-Augmentation Transformations for Risk-Sensitive Reinforcement Learning

no code implementations16 Apr 2018 Shuai Ma, Jia Yuan Yu

In the framework of MDP, although the general reward function takes three arguments-current state, action, and successor state; it is often simplified to a function of two arguments-current state and action.

Q-Learning reinforcement-learning +1

Transition-based versus State-based Reward Functions for MDPs with Value-at-Risk

no code implementations7 Dec 2016 Shuai Ma, Jia Yuan Yu

Thirdly, since the estimation method is for a Markov reward process with the reward function on current state only, we present a transformation algorithm for the Markov reward process with the reward function on current and next states, in order to estimate the VaR function with an intact total reward distribution.

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