Search Results for author: Hao Yu

Found 75 papers, 26 papers with code

Lexicon-Based Graph Convolutional Network for Chinese Word Segmentation

no code implementations Findings (EMNLP) 2021 Kaiyu Huang, Hao Yu, Junpeng Liu, Wei Liu, Jingxiang Cao, Degen Huang

Experimental results on five benchmarks and four cross-domain datasets show the lexicon-based graph convolutional network successfully captures the information of candidate words and helps to improve performance on the benchmarks (Bakeoff-2005 and CTB6) and the cross-domain datasets (SIGHAN-2010).

Chinese Word Segmentation

Personalized Federated Continual Learning via Multi-granularity Prompt

1 code implementation27 Jun 2024 Hao Yu, Xin Yang, Xin Gao, Yan Kang, Hao Wang, Junbo Zhang, Tianrui Li

In addition, we design a selective prompt fusion mechanism for aggregating knowledge of global prompts distilled from different clients.

Continual Learning Personalized Federated Learning

Effectively Compress KV Heads for LLM

no code implementations11 Jun 2024 Hao Yu, Zelan Yang, Shen Li, Yong Li, Jianxin Wu

The advent of pre-trained large language models (LLMs) has revolutionized various natural language processing tasks.

Unified Low-rank Compression Framework for Click-through Rate Prediction

1 code implementation28 May 2024 Hao Yu, Minghao Fu, Jiandong Ding, Yusheng Zhou, Jianxin Wu

To address these challenges, we propose a unified low-rank decomposition framework for compressing CTR prediction models.

Click-Through Rate Prediction Low-rank compression +1

Evaluation of Retrieval-Augmented Generation: A Survey

1 code implementation13 May 2024 Hao Yu, Aoran Gan, Kai Zhang, Shiwei Tong, Qi Liu, Zhaofeng Liu

Retrieval-Augmented Generation (RAG) has recently gained traction in natural language processing.

Information Retrieval RAG +1

Rethinking Efficient and Effective Point-based Networks for Event Camera Classification and Regression: EventMamba

no code implementations9 May 2024 Hongwei Ren, Yue Zhou, Jiadong Zhu, Haotian Fu, Yulong Huang, Xiaopeng Lin, Yuetong Fang, Fei Ma, Hao Yu, Bojun Cheng

However, this approach neglects the sparsity of event data, loses fine-grained temporal information during the transformation process, and increases the computational burden, making it ineffective for characterizing event camera properties.

Temporal Information Extraction

FedProK: Trustworthy Federated Class-Incremental Learning via Prototypical Feature Knowledge Transfer

no code implementations4 May 2024 Xin Gao, Xin Yang, Hao Yu, Yan Kang, Tianrui Li

Federated Class-Incremental Learning (FCIL) focuses on continually transferring the previous knowledge to learn new classes in dynamic Federated Learning (FL).

Class Incremental Learning Federated Learning +2

AutoWebGLM: Bootstrap And Reinforce A Large Language Model-based Web Navigating Agent

1 code implementation4 Apr 2024 Hanyu Lai, Xiao Liu, Iat Long Iong, Shuntian Yao, Yuxuan Chen, Pengbo Shen, Hao Yu, Hanchen Zhang, Xiaohan Zhang, Yuxiao Dong, Jie Tang

Large language models (LLMs) have fueled many intelligent agent tasks, such as web navigation -- but most existing agents perform far from satisfying in real-world webpages due to three factors: (1) the versatility of actions on webpages, (2) HTML text exceeding model processing capacity, and (3) the complexity of decision-making due to the open-domain nature of web.

Decision Making Language Modelling +1

A Comparative Study of Machine Learning Models Predicting Energetics of Interacting Defects

no code implementations20 Mar 2024 Hao Yu

Furthermore, with synthetic data generate from cluster expansion model at near-DFT levels, we obtained enlarged dataset to assess the demands on data for training accurate prediction models using graph neural networks for systems featuring interacting defects.

Towards a Dynamic Future with Adaptable Computing and Network Convergence (ACNC)

no code implementations12 Mar 2024 Masoud Shokrnezhad, Hao Yu, Tarik Taleb, Richard Li, Kyunghan Lee, Jaeseung Song, Cedric Westphal

Hence, this paper presents the concept of Adaptable CNC (ACNC) as an autonomous Machine Learning (ML)-aided mechanism crafted for the joint orchestration of computing and network resources, catering to dynamic and voluminous user requests with stringent requirements.

Continual Learning Dimensionality Reduction

InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models

2 code implementations11 Mar 2024 Linyi Li, Shijie Geng, Zhenwen Li, Yibo He, Hao Yu, Ziyue Hua, Guanghan Ning, Siwei Wang, Tao Xie, Hongxia Yang

We conduct a systematic evaluation for over 100 latest code LLMs on InfiBench, leading to a series of novel and insightful findings.

Code Generation Question Answering

Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments

no code implementations22 Feb 2024 Yu Gu, Yiheng Shu, Hao Yu, Xiao Liu, Yuxiao Dong, Jie Tang, Jayanth Srinivasa, Hugo Latapie, Yu Su

The applications of large language models (LLMs) have expanded well beyond the confines of text processing, signaling a new era where LLMs are envisioned as generalist language agents capable of operating within complex real-world environments.

Replication of Impedance Identification Experiments on a Reinforcement-Learning-Controlled Digital Twin of Human Elbows

no code implementations5 Feb 2024 Hao Yu, Zebin Huang, Qingbo Liu, Ignacio Carlucho, Mustafa Suphi Erden

We compared the elbow movement controlled by an RL agent with the motion of an actual human elbow in terms of the impedance identified in torque-perturbation experiments.

Reinforcement Learning (RL)

Reviving Undersampling for Long-Tailed Learning

2 code implementations30 Jan 2024 Hao Yu, Yingxiao Du, Jianxin Wu

In this paper, we aim to enhance the accuracy of the worst-performing categories and utilize the harmonic mean and geometric mean to assess the model's performance.

Few-Shot Learning

Federated Continual Learning via Knowledge Fusion: A Survey

no code implementations27 Dec 2023 Xin Yang, Hao Yu, Xin Gao, Hao Wang, Junbo Zhang, Tianrui Li

The key objective of FCL is to fuse heterogeneous knowledge from different clients and retain knowledge of previous tasks while learning on new ones.

Continual Learning Federated Learning

Single-Cell Deep Clustering Method Assisted by Exogenous Gene Information: A Novel Approach to Identifying Cell Types

no code implementations28 Nov 2023 Dayu Hu, Ke Liang, Hao Yu, Xinwang Liu

This model leverages exogenous gene network information to facilitate the clustering process, generating discriminative representations.

Clustering Deep Clustering

Data-Driven Modelling for Harmonic Current Emission in Low-Voltage Grid Using MCReSANet with Interpretability Analysis

no code implementations26 Nov 2023 Jieyu Yao, Hao Yu, Paul Judge, Jiabin Jia, Sasa Djokic, Verner Püvi, Matti Lehtonen, Jan Meyer

The results by feature importance analysis show the detailed relationships between each order of harmonic voltage and current in the distribution system.

Feature Importance

Multimodal deep learning for mapping forest dominant height by fusing GEDI with earth observation data

no code implementations20 Nov 2023 Man Chen, Wenquan Dong, Hao Yu, Iain Woodhouse, Casey M. Ryan, Haoyu Liu, Selena Georgiou, Edward T. A. Mitchard

Consequently, we proposed a novel deep learning framework termed the multi-modal attention remote sensing network (MARSNet) to estimate forest dominant height by extrapolating dominant height derived from GEDI, using Setinel-1 data, ALOS-2 PALSAR-2 data, Sentinel-2 optical data and ancillary data.

Earth Observation Multimodal Deep Learning

Forest aboveground biomass estimation using GEDI and earth observation data through attention-based deep learning

no code implementations6 Nov 2023 Wenquan Dong, Edward T. A. Mitchard, Hao Yu, Steven Hancock, Casey M. Ryan

AU-FC achieved intermediate R2 of 0. 64, RMSE of 44. 92 Mgha-1, and bias of -0. 56 Mg ha-1, outperforming RF but underperforming AU model using spatial information.

Earth Observation

ZooPFL: Exploring Black-box Foundation Models for Personalized Federated Learning

1 code implementation8 Oct 2023 Wang Lu, Hao Yu, Jindong Wang, Damien Teney, Haohan Wang, Yiqiang Chen, Qiang Yang, Xing Xie, Xiangyang Ji

When personalized federated learning (FL) meets large foundation models, new challenges arise from various limitations in resources.

Personalized Federated Learning

Contrastive Continual Multi-view Clustering with Filtered Structural Fusion

no code implementations26 Sep 2023 Xinhang Wan, Jiyuan Liu, Hao Yu, Ao Li, Xinwang Liu, Ke Liang, Zhibin Dong, En Zhu

Precisely, considering that data correlations play a vital role in clustering and prior knowledge ought to guide the clustering process of a new view, we develop a data buffer with fixed size to store filtered structural information and utilize it to guide the generation of a robust partition matrix via contrastive learning.

Clustering Contrastive Learning +1

TMac: Temporal Multi-Modal Graph Learning for Acoustic Event Classification

1 code implementation21 Sep 2023 Meng Liu, Ke Liang, Dayu Hu, Hao Yu, Yue Liu, Lingyuan Meng, Wenxuan Tu, Sihang Zhou, Xinwang Liu

We observe that these audiovisual data naturally have temporal attributes, such as the time information for each frame in the video.

Graph Learning

Modality Unifying Network for Visible-Infrared Person Re-Identification

no code implementations ICCV 2023 Hao Yu, Xu Cheng, Wei Peng, Weihao Liu, Guoying Zhao

Visible-infrared person re-identification (VI-ReID) is a challenging task due to large cross-modality discrepancies and intra-class variations.

Person Re-Identification

Dynamic Hyperbolic Attention Network for Fine Hand-object Reconstruction

no code implementations ICCV 2023 Zhiying Leng, Shun-Cheng Wu, Mahdi Saleh, Antonio Montanaro, Hao Yu, Yin Wang, Nassir Navab, Xiaohui Liang, Federico Tombari

In this work, we propose the first precise hand-object reconstruction method in hyperbolic space, namely Dynamic Hyperbolic Attention Network (DHANet), which leverages intrinsic properties of hyperbolic space to learn representative features.

Object Object Reconstruction

Open, Closed, or Small Language Models for Text Classification?

no code implementations19 Aug 2023 Hao Yu, Zachary Yang, Kellin Pelrine, Jean Francois Godbout, Reihaneh Rabbany

Recent advancements in large language models have demonstrated remarkable capabilities across various NLP tasks.

Misinformation Model Selection +4

AgentBench: Evaluating LLMs as Agents

1 code implementation7 Aug 2023 Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, Shudan Zhang, Xiang Deng, Aohan Zeng, Zhengxiao Du, Chenhui Zhang, Sheng Shen, Tianjun Zhang, Yu Su, Huan Sun, Minlie Huang, Yuxiao Dong, Jie Tang

We present AgentBench, a multi-dimensional evolving benchmark that currently consists of 8 distinct environments to assess LLM-as-Agent's reasoning and decision-making abilities in a multi-turn open-ended generation setting.

Decision Making Instruction Following

G$^2$uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clustering

no code implementations8 Jun 2023 Hao Yu, Chuan Ma, Meng Liu, Tianyu Du, Ming Ding, Tao Xiang, Shouling Ji, Xinwang Liu

Through empirical evaluation, comparing G$^2$uardFL with cutting-edge defenses, such as FLAME (USENIX Security 2022) [28] and DeepSight (NDSS 2022) [36], against various backdoor attacks including 3DFed (SP 2023) [20], our results demonstrate its significant effectiveness in mitigating backdoor attacks while having a negligible impact on the aggregated model's performance on benign samples (i. e., the primary task performance).

Anomaly Detection Clustering +2

Online Camera-to-ground Calibration for Autonomous Driving

no code implementations30 Mar 2023 Binbin Li, Xinyu Du, Yao Hu, Hao Yu, Wende Zhang

Online camera-to-ground calibration is to generate a non-rigid body transformation between the camera and the road surface in a real-time manner.

Autonomous Driving Diversity

Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registration

1 code implementation CVPR 2023 Zheng Qin, Hao Yu, Changjian Wang, Yuxing Peng, Kai Xu

We first design a local spatial consistency measure over the deformation graph of the point cloud, which evaluates the spatial compatibility only between the correspondences in the vicinity of a graph node.

Point Cloud Registration

Rotation-Invariant Transformer for Point Cloud Matching

1 code implementation CVPR 2023 Hao Yu, Zheng Qin, Ji Hou, Mahdi Saleh, Dongsheng Li, Benjamin Busam, Slobodan Ilic

To this end, we introduce RoITr, a Rotation-Invariant Transformer to cope with the pose variations in the point cloud matching task.

Data Augmentation Decoder

RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registration

1 code implementation27 Sep 2022 Hao Yu, Ji Hou, Zheng Qin, Mahdi Saleh, Ivan Shugurov, Kai Wang, Benjamin Busam, Slobodan Ilic

More specifically, 3D structures of the whole frame are first represented by our global PPF signatures, from which structural descriptors are learned to help geometric descriptors sense the 3D world beyond local regions.

Point Cloud Registration

PanGu-Coder: Program Synthesis with Function-Level Language Modeling

1 code implementation22 Jul 2022 Fenia Christopoulou, Gerasimos Lampouras, Milan Gritta, Guchun Zhang, Yinpeng Guo, Zhongqi Li, Qi Zhang, Meng Xiao, Bo Shen, Lin Li, Hao Yu, Li Yan, Pingyi Zhou, Xin Wang, Yuchi Ma, Ignacio Iacobacci, Yasheng Wang, Guangtai Liang, Jiansheng Wei, Xin Jiang, Qianxiang Wang, Qun Liu

We present PanGu-Coder, a pretrained decoder-only language model adopting the PanGu-Alpha architecture for text-to-code generation, i. e. the synthesis of programming language solutions given a natural language problem description.

Code Generation Decoder +3

Training Vision Transformers with Only 2040 Images

2 code implementations26 Jan 2022 Yun-Hao Cao, Hao Yu, Jianxin Wu

Vision Transformers (ViTs) is emerging as an alternative to convolutional neural networks (CNNs) for visual recognition.

Inductive Bias

A Unified Pruning Framework for Vision Transformers

1 code implementation30 Nov 2021 Hao Yu, Jianxin Wu

Recently, vision transformer (ViT) and its variants have achieved promising performances in various computer vision tasks.

Model Compression object-detection +1

Mixup Without Hesitation

1 code implementation12 Jan 2021 Hao Yu, Huanyu Wang, Jianxin Wu

In this paper, we find that mixup constantly explores the representation space, and inspired by the exploration-exploitation dilemma in reinforcement learning, we propose mixup Without hesitation (mWh), a concise, effective, and easy-to-use training algorithm.

Data Augmentation Image Classification +2

Robust Attacks on Deep Learning Face Recognition in the Physical World

no code implementations27 Nov 2020 Meng Shen, Hao Yu, Liehuang Zhu, Ke Xu, Qi Li, Xiaojiang Du

Deep neural networks (DNNs) have been increasingly used in face recognition (FR) systems.

Face Recognition

Dynamic Phase Diagram of an Orthogonal Spin Torque device: Topological Category

no code implementations2 Oct 2020 Yuan Hui, Zheng Yang, Hao Yu

The magnetization evolution of the free layer in an orthogonal spin-torque device is studied based on a macrospin model.

Mesoscale and Nanoscale Physics

HOTCAKE: Higher Order Tucker Articulated Kernels for Deeper CNN Compression

no code implementations28 Feb 2020 Rui Lin, Ching-Yun Ko, Zhuolun He, Cong Chen, Yuan Cheng, Hao Yu, Graziano Chesi, Ngai Wong

The emerging edge computing has promoted immense interests in compacting a neural network without sacrificing much accuracy.

Edge-computing Tensor Decomposition

Crude oil price forecasting incorporating news text

no code implementations19 Jan 2020 Yun Bai, Xixi Li, Hao Yu, Suling Jia

Sparse and short news headlines can be arbitrary, noisy, and ambiguous, making it difficult for classic topic model LDA (latent Dirichlet allocation) designed for accommodating long text to discover knowledge from them.

A Communication Efficient Stochastic Multi-Block Alternating Direction Method of Multipliers

no code implementations NeurIPS 2019 Hao Yu

In this paper, we propose a new parallel multi-block stochastic ADMM for distributed stochastic optimization, where each node is only required to perform simple stochastic gradient descent updates.

Stochastic Optimization

On the Computation and Communication Complexity of Parallel SGD with Dynamic Batch Sizes for Stochastic Non-Convex Optimization

no code implementations10 May 2019 Hao Yu, Rong Jin

We show that for stochastic non-convex optimization under the P-L condition, the classical data-parallel SGD with exponentially increasing batch sizes can achieve the fastest known $O(1/(NT))$ convergence with linear speedup using only $\log(T)$ communication rounds.

Stochastic Optimization

On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimization

no code implementations9 May 2019 Hao Yu, Rong Jin, Sen yang

Recent developments on large-scale distributed machine learning applications, e. g., deep neural networks, benefit enormously from the advances in distributed non-convex optimization techniques, e. g., distributed Stochastic Gradient Descent (SGD).

BIG-bench Machine Learning

Solving Non-smooth Constrained Programs with Lower Complexity than \mathcal{O}(1/\varepsilon): A Primal-Dual Homotopy Smoothing Approach

no code implementations NeurIPS 2018 Xiaohan Wei, Hao Yu, Qing Ling, Michael Neely

In this paper, we show that by leveraging a local error bound condition on the dual function, the proposed algorithm can achieve a better primal convergence time of $\mathcal{O}\l(\varepsilon^{-2/(2+\beta)}\log_2(\varepsilon^{-1})\r)$, where $\beta\in(0, 1]$ is a local error bound parameter.

Distributed Optimization

MOHONE: Modeling Higher Order Network Effects in KnowledgeGraphs via Network Infused Embeddings

no code implementations1 Nov 2018 Hao Yu, Vivek Kulkarni, William Wang

First, we introduce methods that learn network representations of entities in the knowledge graph capturing these varied aspects of similarity.

Knowledge Graph Embedding Knowledge Graph Embeddings +2

Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning

no code implementations17 Jul 2018 Hao Yu, Sen yang, Shenghuo Zhu

Ideally, parallel mini-batch SGD can achieve a linear speed-up of the training time (with respect to the number of workers) compared with SGD over a single worker.

Fast K-Means Clustering with Anderson Acceleration

no code implementations27 May 2018 Juyong Zhang, Yuxin Yao, Yue Peng, Hao Yu, Bailin Deng

We propose a novel method to accelerate Lloyd's algorithm for K-Means clustering.

Clustering

DEEPEYE: A Compact and Accurate Video Comprehension at Terminal Devices Compressed with Quantization and Tensorization

no code implementations21 May 2018 Yuan Cheng, Guangya Li, Hai-Bao Chen, Sheldon X. -D. Tan, Hao Yu

As it requires a huge number of parameters when exposed to high dimensional inputs in video detection and classification, there is a grand challenge to develop a compact yet accurate video comprehension at terminal devices.

Action Recognition General Classification +5

Loss Rank Mining: A General Hard Example Mining Method for Real-time Detectors

no code implementations10 Apr 2018 Hao Yu, Zhaoning Zhang, Zheng Qin, Hao Wu, Dongsheng Li, Jun Zhao, Xicheng Lu

LRM is a general method for real-time detectors, as it utilizes the final feature map which exists in all real-time detectors to mine hard examples.

Merging and Evolution: Improving Convolutional Neural Networks for Mobile Applications

2 code implementations24 Mar 2018 Zheng Qin, Zhaoning Zhang, Shiqing Zhang, Hao Yu, Yuxing Peng

Compact neural networks are inclined to exploit "sparsely-connected" convolutions such as depthwise convolution and group convolution for employment in mobile applications.

Online Convex Optimization with Stochastic Constraints

no code implementations NeurIPS 2017 Hao Yu, Michael J. Neely, Xiaohan Wei

This paper considers online convex optimization (OCO) with stochastic constraints, which generalizes Zinkevich's OCO over a known simple fixed set by introducing multiple stochastic functional constraints that are i. i. d.

Scheduling

S-OHEM: Stratified Online Hard Example Mining for Object Detection

no code implementations5 May 2017 Minne Li, Zhaoning Zhang, Hao Yu, Xinyuan Chen, Dongsheng Li

S-OHEM exploits OHEM with stratified sampling, a widely-adopted sampling technique, to choose the training examples according to this influence during hard example mining, and thus enhance the performance of object detectors.

object-detection Object Detection

A GPU-Outperforming FPGA Accelerator Architecture for Binary Convolutional Neural Networks

no code implementations20 Feb 2017 Yixing Li, Zichuan Liu, Kai Xu, Hao Yu, Fengbo Ren

For processing static data in large batch sizes, the proposed solution is on a par with a Titan X GPU in terms of throughput while delivering 9. 5x higher energy efficiency.

A Binary Convolutional Encoder-decoder Network for Real-time Natural Scene Text Processing

no code implementations12 Dec 2016 Zichuan Liu, Yixing Li, Fengbo Ren, Hao Yu

In this paper, we develop a binary convolutional encoder-decoder network (B-CEDNet) for natural scene text processing (NSTP).

Decoder

A Low Complexity Algorithm with $O(\sqrt{T})$ Regret and $O(1)$ Constraint Violations for Online Convex Optimization with Long Term Constraints

no code implementations8 Apr 2016 Hao Yu, Michael J. Neely

That prior work proposes an algorithm to achieve $O(\sqrt{T})$ regret and $O(T^{3/4})$ constraint violations for general problems and another algorithm to achieve an $O(T^{2/3})$ bound for both regret and constraint violations when the constraint set can be described by a finite number of linear constraints.

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