Search Results for author: Huan Zhao

Found 53 papers, 21 papers with code

Towards Versatile Graph Learning Approach: from the Perspective of Large Language Models

no code implementations18 Feb 2024 Lanning Wei, Jun Gao, Huan Zhao, Quanming Yao

This paper proposes a novel conceptual prototype for designing versatile graph learning methods with LLMs, with a particular focus on the "where" and "how" perspectives.

Feature Engineering Graph Learning +1

EventRL: Enhancing Event Extraction with Outcome Supervision for Large Language Models

no code implementations18 Feb 2024 Jun Gao, Huan Zhao, Wei Wang, Changlong Yu, Ruifeng Xu

In this study, we present EventRL, a reinforcement learning approach developed to enhance event extraction for large language models (LLMs).

Event Extraction Hallucination +1

Towards Fair, Robust and Efficient Client Contribution Evaluation in Federated Learning

no code implementations6 Feb 2024 Meiying Zhang, Huan Zhao, Sheldon Ebron, Kan Yang

In this paper, we introduce a novel method called Fair, Robust, and Efficient Client Assessment (FRECA) for quantifying client contributions in FL.

Federated Learning

Power System Fault Diagnosis with Quantum Computing and Efficient Gate Decomposition

no code implementations18 Jan 2024 Xiang Fei, Huan Zhao, Xiyuan Zhou, Junhua Zhao, Ting Shu, Fushuan Wen

Power system fault diagnosis is crucial for identifying the location and causes of faults and providing decision-making support for power dispatchers.

Combinatorial Optimization Decision Making

Free Lunch for Federated Remote Sensing Target Fine-Grained Classification: A Parameter-Efficient Framework

no code implementations3 Jan 2024 Shengchao Chen, Ting Shu, Huan Zhao, Jiahao Wang, Sufen Ren, Lina Yang

Remote Sensing Target Fine-grained Classification (TFGC) is of great significance in both military and civilian fields.

Federated Learning

Multi-Criteria Client Selection and Scheduling with Fairness Guarantee for Federated Learning Service

no code implementations5 Dec 2023 Meiying Zhang, Huan Zhao, Sheldon Ebron, Ruitao Xie, Kan Yang

Then, we formulate the initial client pool selection problem into an optimization problem that aims to maximize the overall scores of selected clients within a given budget and propose a greedy algorithm to solve it.

Fairness Federated Learning +1

Applying Large Language Models to Power Systems: Potential Security Threats

no code implementations22 Nov 2023 Jiaqi Ruan, Gaoqi Liang, Huan Zhao, Guolong Liu, Xianzhuo Sun, Jing Qiu, Zhao Xu, Fushuan Wen, Zhao Yang Dong

Applying large language models (LLMs) to modern power systems presents a promising avenue for enhancing decision-making and operational efficiency.

Decision Making

Evaluating Large Language Models in Ophthalmology

no code implementations7 Nov 2023 Jason Holmes, Shuyuan Ye, Yiwei Li, Shi-Nan Wu, Zhengliang Liu, Zihao Wu, Jinyu Hu, Huan Zhao, Xi Jiang, Wei Liu, Hong Wei, Jie Zou, Tianming Liu, Yi Shao

Methods: A 100-item ophthalmology single-choice test was administered to three different LLMs (GPT-3. 5, GPT-4, and PaLM2) and three different professional levels (medical undergraduates, medical masters, and attending physicians), respectively.

Decision Making

Evaluating multiple large language models in pediatric ophthalmology

no code implementations7 Nov 2023 Jason Holmes, Rui Peng, Yiwei Li, Jinyu Hu, Zhengliang Liu, Zihao Wu, Huan Zhao, Xi Jiang, Wei Liu, Hong Wei, Jie Zou, Tianming Liu, Yi Shao

IMPORTANCE The response effectiveness of different large language models (LLMs) and various individuals, including medical students, graduate students, and practicing physicians, in pediatric ophthalmology consultations, has not been clearly established yet.

Multiple-choice

Unleashing the Power of Graph Learning through LLM-based Autonomous Agents

no code implementations8 Sep 2023 Lanning Wei, Zhiqiang He, Huan Zhao, Quanming Yao

With these agents, those components are processed by decomposing and completing step by step, thereby generating a solution for the given data automatically, regardless of the learning task on node or graph.

AutoML Graph Learning

Refashioning Emotion Recognition Modelling: The Advent of Generalised Large Models

no code implementations21 Aug 2023 Zixing Zhang, Liyizhe Peng, Tao Pang, Jing Han, Huan Zhao, Bjorn W. Schuller

After the inception of emotion recognition or affective computing, it has increasingly become an active research topic due to its broad applications.

Emotion Recognition Few-Shot Learning +1

Automated 3D Pre-Training for Molecular Property Prediction

1 code implementation13 Jun 2023 Xu Wang, Huan Zhao, WeiWei Tu, Quanming Yao

Next, to automatically fuse these three generative tasks, we design a surrogate metric using the \textit{total energy} to search for weight distribution of the three pretext task since total energy corresponding to the quality of 3D conformer. Extensive experiments on 2D molecular graphs are conducted to demonstrate the accuracy, efficiency and generalization ability of the proposed 3D PGT compared to various pre-training baselines.

Drug Discovery Graph Learning +3

MASK-CNN-Transformer For Real-Time Multi-Label Weather Recognition

no code implementations28 Apr 2023 Shengchao Chen, Ting Shu, Huan Zhao, Yuan Yan Tang

The proposed model called MASK-Convolutional Neural Network-Transformer (MASK-CT) is based on the Transformer, the convolutional process, and the MASK mechanism.

TempEE: Temporal-Spatial Parallel Transformer for Radar Echo Extrapolation Beyond Auto-Regression

no code implementations27 Apr 2023 Shengchao Chen, Ting Shu, Huan Zhao, Guo Zhong, Xunlai Chen

TempEE avoids using auto-regression and instead employs a one-step forward strategy to prevent cumulative error spreading during the extrapolation process.

regression

Exploring the Feasibility of ChatGPT for Event Extraction

no code implementations7 Mar 2023 Jun Gao, Huan Zhao, Changlong Yu, Ruifeng Xu

While ChatGPT has demonstrated impressive results in tasks like machine translation, text summarization, and question answering, it presents challenges when used for complex tasks like event extraction.

Event Extraction Machine Translation +2

Enhancing Intra-class Information Extraction for Heterophilous Graphs: One Neural Architecture Search Approach

no code implementations20 Nov 2022 Lanning Wei, Zhiqiang He, Huan Zhao, Quanming Yao

Despite the success, we observe two aspects that can be further improved: (a) enhancing the ego feature information extraction from node itself which is more reliable in extracting the intra-class information; (b) designing node-wise GNNs can better adapt to the nodes with different homophily ratios.

Graph Representation Learning Neural Architecture Search +1

TSUP Speaker Diarization System for Conversational Short-phrase Speaker Diarization Challenge

no code implementations26 Oct 2022 Bowen Pang, Huan Zhao, Gaosheng Zhang, Xiaoyue Yang, Yang Sun, Li Zhang, Qing Wang, Lei Xie

In this challenge, we explore three kinds of typical speaker diarization systems, which are spectral clustering(SC) based diarization, target-speaker voice activity detection(TS-VAD) and end-to-end neural diarization(EEND) respectively.

Action Detection Activity Detection +2

Graph Property Prediction on Open Graph Benchmark: A Winning Solution by Graph Neural Architecture Search

1 code implementation13 Jul 2022 Xu Wang, Huan Zhao, Lanning Wei, Quanming Yao

Aiming at two molecular graph datasets and one protein association subgraph dataset in OGB graph classification task, we design a graph neural network framework for graph classification task by introducing PAS(Pooling Architecture Search).

feature selection Graph Classification +3

Bridging the Gap of AutoGraph between Academia and Industry: Analysing AutoGraph Challenge at KDD Cup 2020

1 code implementation6 Apr 2022 Zhen Xu, Lanning Wei, Huan Zhao, Rex Ying, Quanming Yao, Wei-Wei Tu, Isabelle Guyon

Researchers naturally adopt Automated Machine Learning on Graph Learning, aiming to reduce the human effort and achieve generally top-performing GNNs, but their methods focus more on the architecture search.

Graph Learning Neural Architecture Search +1

Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network

1 code implementation18 Feb 2022 Tianyu Zhao, Cheng Yang, Yibo Li, Quan Gan, Zhenyi Wang, Fengqi Liang, Huan Zhao, Yingxia Shao, Xiao Wang, Chuan Shi

Heterogeneous Graph Neural Network (HGNN) has been successfully employed in various tasks, but we cannot accurately know the importance of different design dimensions of HGNNs due to diverse architectures and applied scenarios.

Graph Neural Networks for Double-Strand DNA Breaks Prediction

no code implementations4 Jan 2022 Xu Wang, Huan Zhao, WeiWei Tu, Hao Li, Yu Sun, Xiaochen Bo

Double-strand DNA breaks (DSBs) are a form of DNA damage that can cause abnormal chromosomal rearrangements.

Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective

2 code implementations29 Dec 2021 Lanning Wei, Huan Zhao, Zhiqiang He

To enjoy the benefits while alleviating the corresponding deficiencies of these two manners, we learn to design the topology of GNNs in a novel feature fusion perspective which is dubbed F$^2$GNN.

feature selection Neural Architecture Search

Learn Layer-wise Connections in Graph Neural Networks

no code implementations27 Dec 2021 Lanning Wei, Huan Zhao, Zhiqiang He

In recent years, Graph Neural Networks (GNNs) have shown superior performance on diverse applications on real-world datasets.

Neural Architecture Search

Nondestructive Testing of Composite Fibre Materials with Hyperspectral Imaging : Evaluative Studies in the EU H2020 FibreEUse Project

no code implementations4 Nov 2021 Yijun Yan, Jinchang Ren, Huan Zhao, James F. C. Windmill, Winifred Ijomah, Jesper de Wit, Justus von Freeden

Through capturing spectral data from a wide frequency range along with the spatial information, hyperspectral imaging (HSI) can detect minor differences in terms of temperature, moisture and chemical composition.

Codabench: Flexible, Easy-to-Use and Reproducible Benchmarking Platform

2 code implementations12 Oct 2021 Zhen Xu, Sergio Escalera, Isabelle Guyon, Adrien Pavão, Magali Richard, Wei-Wei Tu, Quanming Yao, Huan Zhao

A public instance of Codabench (https://www. codabench. org/) is open to everyone, free of charge, and allows benchmark organizers to compare fairly submissions, under the same setting (software, hardware, data, algorithms), with custom protocols and data formats.

Benchmarking

Multi-Relational Graph based Heterogeneous Multi-Task Learning in Community Question Answering

no code implementations4 Sep 2021 Zizheng Lin, Haowen Ke, Ngo-Yin Wong, Jiaxin Bai, Yangqiu Song, Huan Zhao, Junpeng Ye

To tackle this challenge, we develop a multi-relational graph based MTL model called Heterogeneous Multi-Task Graph Isomorphism Network (HMTGIN) which efficiently solves heterogeneous CQA tasks.

Community Question Answering Multi-Task Learning

Pooling Architecture Search for Graph Classification

3 code implementations24 Aug 2021 Lanning Wei, Huan Zhao, Quanming Yao, Zhiqiang He

To address this problem, we propose to use neural architecture search (NAS) to search for adaptive pooling architectures for graph classification.

Graph Classification Neural Architecture Search

TabGNN: Multiplex Graph Neural Network for Tabular Data Prediction

1 code implementation20 Aug 2021 Xiawei Guo, Yuhan Quan, Huan Zhao, Quanming Yao, Yong Li, WeiWei Tu

Tabular data prediction (TDP) is one of the most popular industrial applications, and various methods have been designed to improve the prediction performance.

Search to aggregate neighborhood for graph neural network

no code implementations14 Apr 2021 Huan Zhao, Quanming Yao, WeiWei Tu

In this work, to obtain the data-specific GNN architectures and address the computational challenges facing by NAS approaches, we propose a framework, which tries to Search to Aggregate NEighborhood (SANE), to automatically design data-specific GNN architectures.

Neural Architecture Search

Efficient Graph Neural Architecture Search

no code implementations1 Jan 2021 Huan Zhao, Lanning Wei, Quanming Yao, Zhiqiang He

To obtain state-of-the-art (SOAT) data-specific GNN architectures, researchers turn to the neural architecture search (NAS) methods.

Neural Architecture Search Transfer Learning

DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks

2 code implementations7 Oct 2020 Yuhui Ding, Quanming Yao, Huan Zhao, Tong Zhang

Specifically, we search for a meta graph, which can capture more complex semantic relations than a meta path, to determine how graph neural networks (GNNs) propagate messages along different types of edges.

Neural Architecture Search Recommendation Systems

Simplifying Architecture Search for Graph Neural Network

2 code implementations26 Aug 2020 Huan Zhao, Lanning Wei, Quanming Yao

Recent years have witnessed the popularity of Graph Neural Networks (GNN) in various scenarios.

Neural Architecture Search

Phase-coherent asynchronous optical sampling system

no code implementations7 Aug 2020 Honglei Yang, Shengkang Zhang, Huan Zhao, Jun Ge

Mutual phase coherence is the most crucial factor in asynchronous optical sampling system, and its enhancement is commonly achieved by phase-locking both femtosecond lasers to a shared narrow-linewidth cavity-stabilized laser.

Optics Instrumentation and Detectors

Motif Enhanced Recommendation over Heterogeneous Information Network

1 code implementation26 Aug 2019 Huan Zhao, Yingqi Zhou, Yangqiu Song, Dik Lun Lee

In this paper, we propose to use motifs to capture higher-order relations among nodes of same type in a HIN and develop the motif-enhanced meta-path (MEMP) to combine motif-based higher-order relations with edge-based first-order relations.

Recommendation Systems

Beyond Personalization: Social Content Recommendation for Creator Equality and Consumer Satisfaction

1 code implementation28 May 2019 Wenyi Xiao, Huan Zhao, Haojie Pan, Yangqiu Song, Vincent W. Zheng, Qiang Yang

An effective content recommendation in modern social media platforms should benefit both creators to bring genuine benefits to them and consumers to help them get really interesting content.

POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashion

1 code implementation6 May 2019 Wen Chen, Pipei Huang, Jiaming Xu, Xin Guo, Cheng Guo, Fei Sun, Chao Li, Andreas Pfadler, Huan Zhao, Binqiang Zhao

In particular, there exist two requirements for fashion outfit recommendation: the Compatibility of the generated fashion outfits, and the Personalization in the recommendation process.

Multi-Interest Network with Dynamic Routing for Recommendation at Tmall

5 code implementations17 Apr 2019 Chao Li, Zhiyuan Liu, Mengmeng Wu, Yuchi Xu, Pipei Huang, Huan Zhao, Guoliang Kang, Qiwei Chen, Wei Li, Dik Lun Lee

Industrial recommender systems usually consist of the matching stage and the ranking stage, in order to handle the billion-scale of users and items.

Clustering Information Retrieval +1

A General End-to-end Diagnosis Framework for Manufacturing Systems

no code implementations17 Dec 2018 Ye Yuan, Guijun Ma, Cheng Cheng, Beitong Zhou, Huan Zhao, Hai-Tao Zhang, Han Ding

A central challenge in manufacturing sector lies in the requirement of a general framework to ensure satisfied diagnosis and monitoring performances in different manufacturing applications.

Management

Automated Machine Learning: From Principles to Practices

1 code implementation31 Oct 2018 Zhenqian Shen, Yongqi Zhang, Lanning Wei, Huan Zhao, Quanming Yao

Machine learning (ML) methods have been developing rapidly, but configuring and selecting proper methods to achieve a desired performance is increasingly difficult and tedious.

BIG-bench Machine Learning Neural Architecture Search

Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba

2 code implementations KDD 2018 Jizhe Wang, Pipei Huang, Huan Zhao, Zhibo Zhang, Binqiang Zhao, Dik Lun Lee

Using online A/B test, we show that the online Click-Through-Rate (CTRs) are improved comparing to the previous recommendation methods widely used in Taobao, further demonstrating the effectiveness and feasibility of our proposed methods in Taobao's live production environment.

Graph Embedding Recommendation Systems

Side Information Fusion for Recommender Systems over Heterogeneous Information Network

1 code implementation8 Jan 2018 Huan Zhao, Quanming Yao, Yangqiu Song, James Kwok, Dik Lun Lee

Collaborative filtering (CF) has been one of the most important and popular recommendation methods, which aims at predicting users' preferences (ratings) based on their past behaviors.

Collaborative Filtering Recommendation Systems

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