Search Results for author: Yiyuan Yang

Found 17 papers, 11 papers with code

Large Language Models as Efficient Reward Function Searchers for Custom-Environment Multi-Objective Reinforcement Learning

no code implementations4 Sep 2024 Guanwen Xie, Jingzehua Xu, Yiyuan Yang, Yimian Ding, Shuai Zhang

Achieving the effective design and improvement of reward functions in reinforcement learning (RL) tasks with complex custom environments and multiple requirements presents considerable challenges.

Long-Context Understanding Multi-Objective Reinforcement Learning +1

Enhancing Information Freshness: An AoI Optimized Markov Decision Process Dedicated In the Underwater Task

no code implementations4 Sep 2024 Jingzehua Xu, Yimian Ding, Yiyuan Yang, Guanwen Xie, Shuai Zhang

However, underwater tasks have mostly failed due to the observation delay caused by acoustic communication in the Internet of underwater things.

Decision Making Reinforcement Learning (RL)

Intelligent Cross-Organizational Process Mining: A Survey and New Perspectives

no code implementations15 Jul 2024 Yiyuan Yang, Zheshun Wu, Yong Chu, Zhenghua Chen, Zenglin Xu, Qingsong Wen

Process mining, as a high-level field in data mining, plays a crucial role in enhancing operational efficiency and decision-making across organizations.

Data Integration Decision Making +2

TSI-Bench: Benchmarking Time Series Imputation

4 code implementations18 Jun 2024 Wenjie Du, Jun Wang, Linglong Qian, Yiyuan Yang, Zina Ibrahim, Fanxing Liu, Zepu Wang, Haoxin Liu, Zhiyuan Zhao, Yingjie Zhou, Wenjia Wang, Kaize Ding, Yuxuan Liang, B. Aditya Prakash, Qingsong Wen

Despite the development of numerous deep learning algorithms for time series imputation, the community lacks standardized and comprehensive benchmark platforms to effectively evaluate imputation performance across different settings.

Benchmarking Deep Learning +3

Pre-training Feature Guided Diffusion Model for Speech Enhancement

no code implementations11 Jun 2024 Yiyuan Yang, Niki Trigoni, Andrew Markham

Speech enhancement significantly improves the clarity and intelligibility of speech in noisy environments, improving communication and listening experiences.

Speech Enhancement

Imitating from auxiliary imperfect demonstrations via Adversarial Density Weighted Regression

1 code implementation28 May 2024 Ziqi Zhang, Zifeng Zhuang, Jingzehua Xu, Yiyuan Yang, Yubo Huang, Donglin Wang, Shuai Zhang

Specifically, ADR addresses several limitations in previous IL algorithms: First, most IL algorithms are based on the Bellman operator, which inevitably suffer from cumulative offsets from sub-optimal rewards during multi-step update processes.

Imitation Learning MuJoCo +3

Unveiling the Secrets: How Masking Strategies Shape Time Series Imputation

1 code implementation26 May 2024 Linglong Qian, Yiyuan Yang, Wenjie Du, Jun Wang, Zina Ibrahim

Time series imputation is a critical challenge in data mining, particularly in domains like healthcare and environmental monitoring, where missing data can compromise analytical outcomes.

Imputation Time Series

A Survey on Diffusion Models for Time Series and Spatio-Temporal Data

1 code implementation29 Apr 2024 Yiyuan Yang, Ming Jin, Haomin Wen, Chaoli Zhang, Yuxuan Liang, Lintao Ma, Yi Wang, Chenghao Liu, Bin Yang, Zenglin Xu, Jiang Bian, Shirui Pan, Qingsong Wen

Conditioned models, on the other hand, utilize extra information to enhance performance and are similarly divided for both predictive and generative tasks.

Anomaly Detection Imputation +1

DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Series

1 code implementation17 Apr 2024 Zahra Zamanzadeh Darban, Yiyuan Yang, Geoffrey I. Webb, Charu C. Aggarwal, Qingsong Wen, Mahsa Salehi

To address this limitation, we propose a novel Domain Adaptation Contrastive learning model for Anomaly Detection in multivariate time series (DACAD), combining UDA with contrastive learning.

Anomaly Detection Contrastive Learning +5

Dual-Personalizing Adapter for Federated Foundation Models

1 code implementation28 Mar 2024 Yiyuan Yang, Guodong Long, Tao Shen, Jing Jiang, Michael Blumenstein

By co-working with a foundation model, a global adapter and a local adapter jointly tackle the test-time distribution shifts and client-specific personalization.

Federated Learning

PatchAD: A Lightweight Patch-based MLP-Mixer for Time Series Anomaly Detection

1 code implementation18 Jan 2024 Zhijie Zhong, Zhiwen Yu, Yiyuan Yang, Weizheng Wang, Kaixiang Yang

Anomaly detection in time series analysis is a pivotal task, yet it poses the challenge of discerning normal and abnormal patterns in label-deficient scenarios.

Anomaly Detection Contrastive Learning +2

AI-Based Energy Transportation Safety: Pipeline Radial Threat Estimation Using Intelligent Sensing System

no code implementations18 Dec 2023 Chengyuan Zhu, Yiyuan Yang, Kaixiang Yang, Haifeng Zhang, Qinmin Yang, C. L. Philip Chen

This refinement is crucial in effectively identifying genuine threats to pipelines, thus enhancing the safety of energy transportation.

Transfer Learning

DynPoint: Dynamic Neural Point For View Synthesis

1 code implementation NeurIPS 2023 Kaichen Zhou, Jia-Xing Zhong, Sangyun Shin, Kai Lu, Yiyuan Yang, Andrew Markham, Niki Trigoni

The introduction of neural radiance fields has greatly improved the effectiveness of view synthesis for monocular videos.

DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection

2 code implementations17 Jun 2023 Yiyuan Yang, Chaoli Zhang, Tian Zhou, Qingsong Wen, Liang Sun

On the other hand, contrastive learning aims to find a representation that can clearly distinguish any instance from the others, which can bring a more natural and promising representation for time series anomaly detection.

Anomaly Detection Contrastive Learning +3

Do Time Constraints Re-Prioritize Attention to Shapes During Visual Photo Inspection?

no code implementations14 Apr 2021 Yiyuan Yang, Kenneth Li, Fernanda Eliott, Maithilee Kunda

People's visual experiences of the world are easy to carve up and examine along natural language boundaries, e. g., by category labels, attribute labels, etc.

Attribute

Internal-transfer Weighting of Multi-task Learning for Lung Cancer Detection

1 code implementation16 Dec 2019 Yiyuan Yang, Riqiang Gao, Yucheng Tang, Sanja L. Antic, Steve Deppen, Yuankai Huo, Kim L. Sandler, Pierre P. Massion, Bennett A. Landman

To improve performance on the primary task, we propose an Internal-Transfer Weighting (ITW) strategy to suppress the loss functions on auxiliary tasks for the final stages of training.

Multi-Task Learning

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