Search Results for author: Yi Zhao

Found 59 papers, 18 papers with code

Bidirectional Hierarchical Attention Networks based on Document-level Context for Emotion Cause Extraction

no code implementations Findings (EMNLP) 2021 Guimin Hu, Guangming Lu, Yi Zhao

Moreover, we quantify the effect of context on emotion cause extraction and provide the visualization of the interactions between candidate cause clauses and contexts.

Emotion Cause Extraction Graph Attention

MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning

no code implementations23 Oct 2024 Jingfan Zhang, Yi Zhao, Dan Chen, Xing Tian, Huanran Zheng, Wei Zhu

Low-rank adaptation (LoRA) and its mixture-of-experts (MOE) variants are highly effective parameter-efficient fine-tuning (PEFT) methods.

Math parameter-efficient fine-tuning

CAP: Data Contamination Detection via Consistency Amplification

no code implementations19 Oct 2024 Yi Zhao, Jing Li, Linyi Yang

Additionally, CAP is applicable to various benchmarks and works for both white-box and black-box models.

PEDRO: Parameter-Efficient Fine-tuning with Prompt DEpenDent Representation MOdification

no code implementations26 Sep 2024 Tianfang Xie, Tianjing Li, Wei Zhu, Wei Han, Yi Zhao

Due to their substantial sizes, large language models (LLMs) are typically deployed within a single-backbone multi-tenant framework.

parameter-efficient fine-tuning

EmotionQueen: A Benchmark for Evaluating Empathy of Large Language Models

no code implementations20 Sep 2024 Yuyan Chen, Hao Wang, Songzhou Yan, Sijia Liu, Yueze Li, Yi Zhao, Yanghua Xiao

The framework includes four distinctive tasks: Key Event Recognition, Mixed Event Recognition, Implicit Emotional Recognition, and Intention Recognition.

Emotional Intelligence Emotion Recognition +2

Irreversibility in Bacterial Regulatory Networks

1 code implementation6 Sep 2024 Yi Zhao, Thomas P. Wytock, Kimberly A. Reynolds, Adilson E. Motter

Irreversibility, in which a transient perturbation leaves a system in a new state, is an emergent property in systems of interacting entities.

VQ-CTAP: Cross-Modal Fine-Grained Sequence Representation Learning for Speech Processing

no code implementations11 Aug 2024 Chunyu Qiang, Wang Geng, Yi Zhao, Ruibo Fu, Tao Wang, Cheng Gong, Tianrui Wang, Qiuyu Liu, Jiangyan Yi, Zhengqi Wen, Chen Zhang, Hao Che, Longbiao Wang, Jianwu Dang, JianHua Tao

For tasks such as text-to-speech (TTS), voice conversion (VC), and automatic speech recognition (ASR), a cross-modal fine-grained (frame-level) sequence representation is desired, emphasizing the semantic content of the text modality while de-emphasizing the paralinguistic information of the speech modality.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Beyond Entity Alignment: Towards Complete Knowledge Graph Alignment via Entity-Relation Synergy

no code implementations25 Jul 2024 Xiaohan Fang, Chaozhuo Li, Yi Zhao, Qian Zang, Litian Zhang, Jiquan Peng, Xi Zhang, Jibing Gong

Knowledge Graph Alignment (KGA) aims to integrate knowledge from multiple sources to address the limitations of individual Knowledge Graphs (KGs) in terms of coverage and depth.

Entity Alignment Knowledge Graphs +1

E-ANT: A Large-Scale Dataset for Efficient Automatic GUI NavigaTion

no code implementations20 Jun 2024 Ke Wang, Tianyu Xia, Zhangxuan Gu, Yi Zhao, Shuheng Shen, Changhua Meng, Weiqiang Wang, Ke Xu

Online GUI navigation on mobile devices has driven a lot of attention recent years since it contributes to many real-world applications.

Decision Making

Research on Driver Facial Fatigue Detection Based on Yolov8 Model

no code implementations4 Jun 2024 Chang Zhou, Yang Zhao, Shaobo Liu, Yi Zhao, Xingchen Li, Chiyu Cheng

In a society where traffic accidents frequently occur, fatigue driving has emerged as a grave issue.

Predict Click-Through Rates with Deep Interest Network Model in E-commerce Advertising

no code implementations4 Jun 2024 Chang Zhou, Yang Zhao, Yuelin Zou, Jin Cao, Wenhan Fan, Yi Zhao, Chiyu Cheng

This paper proposes new methods to enhance click-through rate (CTR) prediction models using the Deep Interest Network (DIN) model, specifically applied to the advertising system of Alibaba's Taobao platform.

Click-Through Rate Prediction

RU22Fact: Optimizing Evidence for Multilingual Explainable Fact-Checking on Russia-Ukraine Conflict

1 code implementation25 Mar 2024 Yirong Zeng, Xiao Ding, Yi Zhao, Xiangyu Li, Jie Zhang, Chao Yao, Ting Liu, Bing Qin

Furthermore, we construct RU22Fact, a novel multilingual explainable fact-checking dataset on the Russia-Ukraine conflict in 2022 of 16K samples, each containing real-world claims, optimized evidence, and referenced explanation.

16k Claim Verification +4

Defending Against Data Reconstruction Attacks in Federated Learning: An Information Theory Approach

no code implementations2 Mar 2024 Qi Tan, Qi Li, Yi Zhao, Zhuotao Liu, Xiaobing Guo, Ke Xu

According to the channel model, we propose algorithms to constrain the information transmitted in a single round of local training.

Federated Learning

VIALM: A Survey and Benchmark of Visually Impaired Assistance with Large Models

no code implementations29 Jan 2024 Yi Zhao, Yilin Zhang, Rong Xiang, Jing Li, Hillming Li

Visually Impaired Assistance (VIA) aims to automatically help the visually impaired (VI) handle daily activities.

MOS-FAD: Improving Fake Audio Detection Via Automatic Mean Opinion Score Prediction

no code implementations24 Jan 2024 Wangjin Zhou, Zhengdong Yang, Chenhui Chu, Sheng Li, Raj Dabre, Yi Zhao, Tatsuya Kawahara

We propose MOS-FAD, where MOS can be leveraged at two key points in FAD: training data selection and model fusion.

FAD

Wavelet Dynamic Selection Network for Inertial Sensor Signal Enhancement

no code implementations29 Dec 2023 Yifeng Wang, Yi Zhao

As a mainstream signal processing method, wavelet is hailed as the mathematical microscope of signal due to the plentiful and diverse wavelet basis functions.

Trajectory Recovery

Two-Stage Adaptive Network for Semi-Supervised Cross-Domain Crater Detection under Varying Scenario Distributions

no code implementations11 Dec 2023 Yifan Liu, Tiecheng Song, Chengye Xian, Ruiyuan Chen, Yi Zhao, Rui Li, Tan Guo

Experimental results on benchmark datasets demonstrate that the proposed network can enhance domain adaptation ability for crater detection under varying scenario distributions.

Domain Generalization Image Augmentation +1

Optimistic Multi-Agent Policy Gradient

1 code implementation3 Nov 2023 Wenshuai Zhao, Yi Zhao, Zhiyuan Li, Juho Kannala, Joni Pajarinen

*Relative overgeneralization* (RO) occurs in cooperative multi-agent learning tasks when agents converge towards a suboptimal joint policy due to overfitting to suboptimal behavior of other agents.

Q-Learning

High-Fidelity Speech Synthesis with Minimal Supervision: All Using Diffusion Models

no code implementations27 Sep 2023 Chunyu Qiang, Hao Li, Yixin Tian, Yi Zhao, Ying Zhang, Longbiao Wang, Jianwu Dang

To address these issues, we propose a minimally-supervised high-fidelity speech synthesis method, where all modules are constructed based on the diffusion models.

Speech Synthesis Text to Speech +1

Simplified Temporal Consistency Reinforcement Learning

1 code implementation15 Jun 2023 Yi Zhao, Wenshuai Zhao, Rinu Boney, Juho Kannala, Joni Pajarinen

This applies when using pure planning with a dynamics model conditioned on the representation, but, also when utilizing the representation as policy and value function features in model-free RL.

Decision Making reinforcement-learning +3

Multi-omics Prediction from High-content Cellular Imaging with Deep Learning

1 code implementation15 Jun 2023 Rahil Mehrizi, Arash Mehrjou, Maryana Alegro, Yi Zhao, Benedetta Carbone, Carl Fishwick, Johanna Vappiani, Jing Bi, Siobhan Sanford, Hakan Keles, Marcus Bantscheff, Cuong Nguyen, Patrick Schwab

High-content cellular imaging, transcriptomics, and proteomics data provide rich and complementary views on the molecular layers of biology that influence cellular states and function.

Robust Divergence Angle for Inter-satellite Laser Communications under Target Deviation Uncertainty

no code implementations13 May 2023 Zhanwei Yu, Yi Zhao, Di Yuan

Simulation results show the approach leads to significantly more robust performance than using the divergence angle as if there is no deviation, or other ad-hoc schemes.

HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer

no code implementations5 May 2023 Shuzhe Wang, Zakaria Laskar, Iaroslav Melekhov, Xiaotian Li, Yi Zhao, Giorgos Tolias, Juho Kannala

In this work, we present a new hierarchical scene coordinate network to predict pixel scene coordinates in a coarse-to-fine manner from a single RGB image.

regression Visual Localization

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

Emotion Prediction Oriented method with Multiple Supervisions for Emotion-Cause Pair Extraction

1 code implementation24 Feb 2023 Guimin Hu, Yi Zhao, Guangming Lu

Emotion-cause pair extraction (ECPE) task aims to extract all the pairs of emotions and their causes from an unannotated emotion text.

Emotion Cause Extraction Emotion-Cause Pair Extraction

UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition

1 code implementation21 Nov 2022 Guimin Hu, Ting-En Lin, Yi Zhao, Guangming Lu, Yuchuan Wu, Yongbin Li

Multimodal sentiment analysis (MSA) and emotion recognition in conversation (ERC) are key research topics for computers to understand human behaviors.

Contrastive Learning Emotion Recognition in Conversation +1

Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning

2 code implementations25 Oct 2022 Yi Zhao, Rinu Boney, Alexander Ilin, Juho Kannala, Joni Pajarinen

Offline reinforcement learning, by learning from a fixed dataset, makes it possible to learn agent behaviors without interacting with the environment.

D4RL Offline RL +3

FedDef: Defense Against Gradient Leakage in Federated Learning-based Network Intrusion Detection Systems

no code implementations8 Oct 2022 Jiahui Chen, Yi Zhao, Qi Li, Xuewei Feng, Ke Xu

Deep learning (DL) methods have been widely applied to anomaly-based network intrusion detection system (NIDS) to detect malicious traffic.

Adversarial Attack Federated Learning +1

Continuous Monte Carlo Graph Search

1 code implementation4 Oct 2022 Kalle Kujanpää, Amin Babadi, Yi Zhao, Juho Kannala, Alexander Ilin, Joni Pajarinen

To address this problem, we propose Continuous Monte Carlo Graph Search (CMCGS), an extension of MCTS to online planning in environments with continuous state and action spaces.

continuous-control Continuous Control +1

CM-MLP: Cascade Multi-scale MLP with Axial Context Relation Encoder for Edge Segmentation of Medical Image

1 code implementation23 Aug 2022 Jinkai Lv, Yuyong Hu, Quanshui Fu, Zhiwang Zhang, Yuqiang Hu, Lin Lv, Guoqing Yang, Jinpeng Li, Yi Zhao

However, those methods have the following challenges when dealing with the edges of the medical images: (1) Previous convolutional-based methods do not focus on the boundary relationship between foreground and background around the segmentation edge, which leads to the degradation of segmentation performance when the edge changes complexly.

Image Segmentation Inductive Bias +3

Pattern formation of parasite-host model induced by fear effect

no code implementations18 May 2022 Yong Ye, Yi Zhao, Jiaying Zhou

In this paper, based on the epidemiological microparasite model, a parasite-host model is established by considering the fear effect of susceptible individuals on infectors.

Fusion of Self-supervised Learned Models for MOS Prediction

no code implementations11 Apr 2022 Zhengdong Yang, Wangjin Zhou, Chenhui Chu, Sheng Li, Raj Dabre, Raphael Rubino, Yi Zhao

This challenge aims to predict MOS scores of synthetic speech on two tracks, the main track and a more challenging sub-track: out-of-domain (OOD).

MC-UNet Multi-module Concatenation based on U-shape Network for Retinal Blood Vessels Segmentation

1 code implementation7 Apr 2022 Ting Zhang, Jun Li, Yi Zhao, Nan Chen, Han Zhou, Hongtao Xu, Zihao Guan, Changcai Yang, Lanyan Xue, Riqing Chen, Lifang Wei

The proposed network structure retains three layers the essential structure of U-Net, in which the atrous convolution combining the multi-kernel pooling blocks are designed to obtain more contextual information.

Segmentation

Reinforced MOOCs Concept Recommendation in Heterogeneous Information Networks

no code implementations8 Mar 2022 Jibing Gong, Yao Wan, Ye Liu, Xuewen Li, Yi Zhao, Cheng Wang, YuTing Lin, Xiaohan Fang, Wenzheng Feng, Jingyi Zhang, Jie Tang

Despite the usefulness of this service, we consider that recommending courses to users directly may neglect their varying degrees of expertise.

Graph Attention Graph Neural Network +2

AdaptCL: Efficient Collaborative Learning with Dynamic and Adaptive Pruning

no code implementations27 Jun 2021 Guangmeng Zhou, Ke Xu, Qi Li, Yang Liu, Yi Zhao

In a highly heterogeneous environment, AdaptCL achieves a training speedup of 6. 2x with a slight loss of accuracy.

Pressure-induced Superconductivity in dual-topological semimetal Pt2HgSe3

no code implementations17 Feb 2021 Cuiying Pei, Suhua Jin, Peihao Huang, Anna Vymazalova, Lingling Gao, Yi Zhao, Weizheng Cao, Changhua Li, Peter Nemes-Incze, Yulin Chen, Hanyu Liu, Gang Li, Yanpeng Qi

Recently monolayer jacutingaite (Pt2HgSe3), a naturally occurring exfoliable mineral, discovered in Brazil in 2008, has been theoretically predicted as a candidate quantum spin Hall system with a 0. 5 eV band gap, while the bulk form is one of only a few known dual-topological insulators which may host different surface states protected by symmetries.

Band Gap Superconductivity Materials Science

Pretraining Strategies, Waveform Model Choice, and Acoustic Configurations for Multi-Speaker End-to-End Speech Synthesis

no code implementations10 Nov 2020 Erica Cooper, Xin Wang, Yi Zhao, Yusuke Yasuda, Junichi Yamagishi

We explore pretraining strategies including choice of base corpus with the aim of choosing the best strategy for zero-shot multi-speaker end-to-end synthesis.

Speech Synthesis

Robust Skeletonization for Plant Root Structure Reconstruction from MRI

no code implementations27 Oct 2020 Jannis Horn, Yi Zhao, Nils Wandel, Magdalena Landl, Andrea Schnepf, Sven Behnke

Structural reconstruction of plant roots from MRI is challenging, because of low resolution and low signal-to-noise ratio of the 3D measurements which may lead to disconnectivities and wrongly connected roots.

Learning Disentangled Phone and Speaker Representations in a Semi-Supervised VQ-VAE Paradigm

1 code implementation21 Oct 2020 Jennifer Williams, Yi Zhao, Erica Cooper, Junichi Yamagishi

Additionally, phones can be recognized from sub-phone VQ codebook indices in our semi-supervised VQ-VAE better than self-supervised with global conditions.

speaker-diarization Speaker Diarization +1

Cross-regional oil palm tree counting and detection via multi-level attention domain adaptation network

1 code implementation26 Aug 2020 Juepeng Zheng, Haohuan Fu, Weijia Li, Wenzhao Wu, Yi Zhao, Runmin Dong, Le Yu

In this paper, we propose a novel domain adaptive oil palm tree detection method, i. e., a Multi-level Attention Domain Adaptation Network (MADAN) to reap cross-regional oil palm tree counting and detection.

Domain Adaptation

PBRnet: Pyramidal Bounding Box Refinement to Improve Object Localization Accuracy

no code implementations10 Mar 2020 Li Xiao, Yufan Luo, Chunlong Luo, Lianhe Zhao, Quanshui Fu, Guoqing Yang, Anpeng Huang, Yi Zhao

Based on these principles, we designed a novel boundary refinement architecture to improve localization accuracy by combining coarse-to-fine framework with feature pyramid structure, named as Pyramidal Bounding Box Refinement network(PBRnet), which parameterizes gradually focused boundary areas of objects and leverages lower-level feature maps to extract finer local information when refining the predicted bounding boxes.

Object Localization

Learning from Suspected Target: Bootstrapping Performance for Breast Cancer Detection in Mammography

no code implementations1 Mar 2020 Li Xiao, Cheng Zhu, Junjun Liu, Chunlong Luo, Peifang Liu, Yi Zhao

It is worth mention that dense breast typically has a higher risk for developing breast cancers and also are harder for cancer detection in diagnosis, and our method outperforms a reported result from performance of radiologists.

Breast Cancer Detection Medical Image Analysis +3

3D U-Net for Segmentation of Plant Root MRI Images in Super-Resolution

no code implementations21 Feb 2020 Yi Zhao, Nils Wandel, Magdalena Landl, Andrea Schnepf, Sven Behnke

Magnetic resonance imaging (MRI) enables plant scientists to non-invasively study root system development and root-soil interaction.

Super-Resolution

Improving Relation Classification by Entity Pair Graph

no code implementations Asian Conference on Machine Learning 2019 Yi Zhao, Huaiyu Wan, Jianwei Gao, Youfang Lin

Existing relation classification approaches mainly rely on exploiting external resources and background knowledge to improve the performance and ignore the correlations between entity pairs which are helpful for relation classification.

Classification General Classification +3

Transferring neural speech waveform synthesizers to musical instrument sounds generation

no code implementations27 Oct 2019 Yi Zhao, Xin Wang, Lauri Juvela, Junichi Yamagishi

Recent neural waveform synthesizers such as WaveNet, WaveGlow, and the neural-source-filter (NSF) model have shown good performance in speech synthesis despite their different methods of waveform generation.

Audio Generation Audio Synthesis +2

Hierarchical Scene Coordinate Classification and Regression for Visual Localization

no code implementations CVPR 2020 Xiaotian Li, Shuzhe Wang, Yi Zhao, Jakob Verbeek, Juho Kannala

In this work, we present a new hierarchical scene coordinate network to predict pixel scene coordinates in a coarse-to-fine manner from a single RGB image.

Classification Data Augmentation +4

A General Deep Learning Framework for Network Reconstruction and Dynamics Learning

1 code implementation30 Dec 2018 Zhang Zhang, Yi Zhao, Jing Liu, Shuo Wang, Ruyi Tao, Ruyue Xin, Jiang Zhang

We exhibit the universality of our framework on different kinds of time-series data: with the same structure, our model can be trained to accurately recover the network structure and predict future states on continuous, discrete, and binary dynamics, and outperforms competing network reconstruction methods.

Time Series Time Series Analysis

Deep Learning-Based Gait Recognition Using Smartphones in the Wild

1 code implementation1 Nov 2018 Qin Zou, Yanling Wang, Qian Wang, Yi Zhao, Qingquan Li

Specifically, a hybrid deep neural network is proposed for robust gait feature representation, where features in the space and time domains are successively abstracted by a convolutional neural network and a recurrent neural network.

Deep Learning Gait Recognition +1

Wasserstein GAN and Waveform Loss-based Acoustic Model Training for Multi-speaker Text-to-Speech Synthesis Systems Using a WaveNet Vocoder

no code implementations31 Jul 2018 Yi Zhao, Shinji Takaki, Hieu-Thi Luong, Junichi Yamagishi, Daisuke Saito, Nobuaki Minematsu

In order to reduce the mismatched characteristics between natural and generated acoustic features, we propose frameworks that incorporate either a conditional generative adversarial network (GAN) or its variant, Wasserstein GAN with gradient penalty (WGAN-GP), into multi-speaker speech synthesis that uses the WaveNet vocoder.

Generative Adversarial Network Speech Synthesis +2

In-Orbit Instrument Performance Study and Calibration for POLAR Polarization Measurements

1 code implementation19 May 2018 Zheng-Heng Li, Merlin Kole, Jian-Chao Sun, Li-Ming Song, Nicolas Produit, Bo-Bing Wu, Tianwei Bao, Tancredi Bernasconi, Franck Cadoux, Yongwei Dong, Minzi Feng, Neal Gauvin, Wojtek Hajdas, Hancheng Li, Lu Li, Xin Liu, Radoslaw Marcinkowski, Martin Pohl, Dominik K. Rybka, Haoli Shi, Jacek Szabelski, Teresa Tymieniecka, Ruijie Wang, Yuanhao Wang, Xing Wen, Xin Wu, Shao-Lin Xiong, Anna Zwolinska, Li Zhang, Lai-Yu Zhang, Shuang-Nan Zhang, Yong-Jie Zhang, Yi Zhao

POLAR is a compact space-borne detector designed to perform reliable measurements of the polarization for transient sources like Gamma-Ray Bursts in the energy range 50-500keV.

Instrumentation and Methods for Astrophysics High Energy Physics - Experiment Instrumentation and Detectors

Granger Mediation Analysis of Multiple Time Series with an Application to fMRI

no code implementations15 Sep 2017 Yi Zhao, Xi Luo

These models not only provide valid causal mediation for time series data but also model the causal dynamics across time.

Time Series Time Series Analysis +1

Pathway Lasso: Estimate and Select Sparse Mediation Pathways with High Dimensional Mediators

no code implementations24 Mar 2016 Yi Zhao, Xi Luo

In many scientific studies, it becomes increasingly important to delineate the causal pathways through a large number of mediators, such as genetic and brain mediators.

Model Selection

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