Search Results for author: Xin He

Found 47 papers, 19 papers with code

Balancing User Preferences by Social Networks: A Condition-Guided Social Recommendation Model for Mitigating Popularity Bias

1 code implementation27 May 2024 Xin He, Wenqi Fan, Ruobing Wang, Yili Wang, Ying Wang, Shirui Pan, Xin Wang

More specifically, CGSoRec first includes a Condition-Guided Social Denoising Model (CSD) to remove redundant social relations in the social network for capturing users' social preferences with items more precisely.


RSDehamba: Lightweight Vision Mamba for Remote Sensing Satellite Image Dehazing

no code implementations16 May 2024 Huiling Zhou, Xianhao Wu, Hongming Chen, Xiang Chen, Xin He

To this end, we propose the first lightweight network on the mamba-based model called RSDhamba in the field of RSID.

Computational Efficiency Image Dehazing +1

Spectral-Spatial Mamba for Hyperspectral Image Classification

no code implementations29 Apr 2024 Lingbo Huang, Yushi Chen, Xin He

Among the many deep models, Transformer has gradually attracted interest for its excellence in modeling the long-range dependencies of spatial-spectral features in HSI.

Classification Computational Efficiency +1

Anchor-based Large Language Models

1 code implementation12 Feb 2024 Jianhui Pang, Fanghua Ye, Derek Fai Wong, Xin He, Wanshun Chen, Longyue Wang

Large language models (LLMs) predominantly employ decoder-only transformer architectures, necessitating the retention of keys/values information for historical tokens to provide contextual information and avoid redundant computation.

Computational Efficiency Decoder +1

UAV-Rain1k: A Benchmark for Raindrop Removal from UAV Aerial Imagery

1 code implementation8 Feb 2024 Wenhui Chang, Hongming Chen, Xin He, Xiang Chen, Liangduo Shen

Raindrops adhering to the lens of UAVs can obstruct visibility of the background scene and degrade image quality.

Rain Removal

Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models

no code implementations6 Jan 2024 Xin He, Longhui Wei, Lingxi Xie, Qi Tian

Multimodal Large Language Models (MLLMs) are experiencing rapid growth, yielding a plethora of noteworthy contributions in recent months.

Instruction Following

Search Optimization with Query Likelihood Boosting and Two-Level Approximate Search for Edge Devices

no code implementations12 Dec 2023 Jianwei Zhang, Helian Feng, Xin He, Grant P. Strimel, Farhad Ghassemi, Ali Kebarighotbi

We present a novel search optimization solution for approximate nearest neighbor (ANN) search on resource-constrained edge devices.


Boosting Segment Anything Model Towards Open-Vocabulary Learning

1 code implementation6 Dec 2023 Xumeng Han, Longhui Wei, Xuehui Yu, Zhiyang Dou, Xin He, Kuiran Wang, Zhenjun Han, Qi Tian

The recent Segment Anything Model (SAM) has emerged as a new paradigmatic vision foundation model, showcasing potent zero-shot generalization and flexible prompting.

Object Object Localization +2

Multiplayer Homicidal Chauffeur Reach-Avoid Games: A Pursuit Enclosure Function Approach

no code implementations4 Nov 2023 Rui Yan, Xiaoming Duan, Rui Zou, Xin He, Zongying Shi, Francesco Bullo

We propose a cooperative strategy for the pursuers based on subgames for multiple pursuers against one evader and optimal task allocation.


SemanticBoost: Elevating Motion Generation with Augmented Textual Cues

no code implementations31 Oct 2023 Xin He, Shaoli Huang, Xiaohang Zhan, Chao Weng, Ying Shan

Our framework comprises a Semantic Enhancement module and a Context-Attuned Motion Denoiser (CAMD).

Minimax Optimal Transfer Learning for Kernel-based Nonparametric Regression

no code implementations21 Oct 2023 Chao Wang, Caixing Wang, Xin He, Xingdong Feng

This paper focuses on investigating the transfer learning problem within the context of nonparametric regression over a reproducing kernel Hilbert space.

regression Transfer Learning

Structural transfer learning of non-Gaussian DAG

no code implementations16 Oct 2023 Mingyang Ren, Xin He, Junhui Wang

Directed acyclic graph (DAG) has been widely employed to represent directional relationships among a set of collected nodes.

Transfer Learning

Towards a Unified Analysis of Kernel-based Methods Under Covariate Shift

1 code implementation NeurIPS 2023 Xingdong Feng, Xin He, Caixing Wang, Chao Wang, Jingnan Zhang

Two types of covariate shift problems are the focus of this paper and the sharp convergence rates are established for a general loss function to provide a unified theoretical analysis, which concurs with the optimal results in literature where the squared loss is used.


Efficient Post-training Quantization with FP8 Formats

2 code implementations26 Sep 2023 Haihao Shen, Naveen Mellempudi, Xin He, Qun Gao, Chang Wang, Mengni Wang

Recent advances in deep learning methods such as LLMs and Diffusion models have created a need for improved quantization methods that can meet the computational demands of these modern architectures while maintaining accuracy.

Image Classification Language Modelling +3

Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs

2 code implementations11 Sep 2023 Wenhua Cheng, Weiwei Zhang, Haihao Shen, Yiyang Cai, Xin He, Kaokao Lv, Yi Liu

Large Language Models (LLMs) have demonstrated exceptional proficiency in language-related tasks, but their deployment poses significant challenges due to substantial memory and storage requirements.


FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs

no code implementations3 Sep 2023 Zhenheng Tang, Yuxin Wang, Xin He, Longteng Zhang, Xinglin Pan, Qiang Wang, Rongfei Zeng, Kaiyong Zhao, Shaohuai Shi, Bingsheng He, Xiaowen Chu

The rapid growth of memory and computation requirements of large language models (LLMs) has outpaced the development of hardware, hindering people who lack large-scale high-end GPUs from training or deploying LLMs.


NeuralMatrix: Compute the Entire Neural Networks with Linear Matrix Operations for Efficient Inference

no code implementations23 May 2023 Ruiqi Sun, Siwei Ye, Jie Zhao, Xin He, Yiran Li, An Zou

The inherent diversity of computation types within individual Deep Neural Network (DNN) models imposes a corresponding need for a varied set of computation units within hardware processors.


BS-GAT Behavior Similarity Based Graph Attention Network for Network Intrusion Detection

no code implementations7 Apr 2023 Yalu Wang, Zhijie Han, Jie Li, Xin He

To address the above issue, this paper proposes a graph neural network algorithm based on behavior similarity (BS-GAT) using graph attention network.

Graph Attention graph construction +2

Lformer: Text-to-Image Generation with L-shape Block Parallel Decoding

no code implementations7 Mar 2023 Jiacheng Li, Longhui Wei, Zongyuan Zhan, Xin He, Siliang Tang, Qi Tian, Yueting Zhuang

To better accelerate the generative transformers while keeping good generation quality, we propose Lformer, a semi-autoregressive text-to-image generation model.

Text-to-Image Generation

NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension

1 code implementation23 Nov 2022 Xin He, Jiangchao Yao, Yuxin Wang, Zhenheng Tang, Ka Chu Cheung, Simon See, Bo Han, Xiaowen Chu

One-shot neural architecture search (NAS) substantially improves the search efficiency by training one supernet to estimate the performance of every possible child architecture (i. e., subnet).

Neural Architecture Search

GPPT: Graph Pre-training and Prompt Tuning to Generalize Graph Neural Networks

1 code implementation SIGKDD 2022 Mingchen Sun, Kaixiong Zhou, Xin He, Ying Wang, Xin Wang

Based on the pre-trained model, we propose the graph prompting function to modify the standalone node into a token pair, and reformulate the downstream node classification looking the same as edge prediction.

Few-Shot Learning Node Classification +3

Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning

1 code implementation6 Jun 2022 Zhenheng Tang, Yonggang Zhang, Shaohuai Shi, Xin He, Bo Han, Xiaowen Chu

In federated learning (FL), model performance typically suffers from client drift induced by data heterogeneity, and mainstream works focus on correcting client drift.

Federated Learning

EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs

1 code implementation30 Nov 2021 Guohao Ying, Xin He, Bin Gao, Bo Han, Xiaowen Chu

Some recent works try to search both generator (G) and discriminator (D), but they suffer from the instability of GAN training.

Image Generation Neural Architecture Search +2

Learning linear non-Gaussian directed acyclic graph with diverging number of nodes

no code implementations1 Nov 2021 Ruixuan Zhao, Xin He, Junhui Wang

The proposed method leverages a novel concept of topological layer to facilitate the DAG learning.

Efficient Learning of Quadratic Variance Function Directed Acyclic Graphs via Topological Layers

no code implementations1 Nov 2021 Wei Zhou, Xin He, Wei Zhong, Junhui Wang

Directed acyclic graph (DAG) models are widely used to represent causal relationships among random variables in many application domains.

Kernel-based estimation for partially functional linear model: Minimax rates and randomized sketches

no code implementations18 Oct 2021 Shaogao Lv, Xin He, Junhui Wang

This paper considers the partially functional linear model (PFLM) where all predictive features consist of a functional covariate and a high dimensional scalar vector.

DeceFL: A Principled Decentralized Federated Learning Framework

1 code implementation15 Jul 2021 Ye Yuan, Jun Liu, Dou Jin, Zuogong Yue, Ruijuan Chen, Maolin Wang, Chuan Sun, Lei Xu, Feng Hua, Xin He, Xinlei Yi, Tao Yang, Hai-Tao Zhang, Shaochun Sui, Han Ding

Although there has been a joint effort in tackling such a critical issue by proposing privacy-preserving machine learning frameworks, such as federated learning, most state-of-the-art frameworks are built still in a centralized way, in which a central client is needed for collecting and distributing model information (instead of data itself) from every other client, leading to high communication pressure and high vulnerability when there exists a failure at or attack on the central client.

Federated Learning Privacy Preserving

Optimizing NLU Reranking Using Entity Resolution Signals in Multi-domain Dialog Systems

no code implementations NAACL 2021 Tong Wang, Jiangning Chen, Mohsen Malmir, Shuyan Dong, Xin He, Han Wang, Chengwei Su, Yue Liu, Yang Liu

In dialog systems, the Natural Language Understanding (NLU) component typically makes the interpretation decision (including domain, intent and slots) for an utterance before the mentioned entities are resolved.

Entity Resolution intent-classification +2

A Competitive Method to VIPriors Object Detection Challenge

no code implementations19 Apr 2021 Fei Shen, Xin He, Mengwan Wei, Yi Xie

In this report, we introduce the technical details of our submission to the VIPriors object detection challenge.

Data Augmentation Object +2

Evolutionary Multi-objective Architecture Search Framework: Application to COVID-19 3D CT Classification

1 code implementation26 Jan 2021 Xin He, Guohao Ying, Jiyong Zhang, Xiaowen Chu

We propose a new objective, namely potential, which can help exploit promising models to indirectly reduce the number of models involved in weights training, thus alleviating search instability.

Computed Tomography (CT) Medical Diagnosis +1

Automated Model Design and Benchmarking of 3D Deep Learning Models for COVID-19 Detection with Chest CT Scans

2 code implementations14 Jan 2021 Xin He, Shihao Wang, Xiaowen Chu, Shaohuai Shi, Jiangping Tang, Xin Liu, Chenggang Yan, Jiyong Zhang, Guiguang Ding

The experimental results show that our automatically searched models (CovidNet3D) outperform the baseline human-designed models on the three datasets with tens of times smaller model size and higher accuracy.

Benchmarking Medical Diagnosis +1

Alpha-DAG: a reinforcement learning based algorithm to learn Directed Acyclic Graphs

no code implementations1 Jan 2021 Fan Zhou, Yifeng Pan, Shenghua Zhu, Xin He

Directed acyclic graphs (DAGs) are widely used to model the casual relationships among random variables in many disciplines.

reinforcement-learning Reinforcement Learning (RL)

Design of Double Auction Mechanism Based on Social Network

no code implementations IEEE Access ( Volume 8) 2020 Junping Xu, Xin He

The goal of this paper is to propose mechanisms such that they can encourage buyers already in the market to invite other potential buyers to join the auction through social networks, and achieve an effective allocation of merchandises and increase profits for sellers, which cannot be achieved under the existing double auction mechanism.

Benchmarking the Performance and Energy Efficiency of AI Accelerators for AI Training

no code implementations15 Sep 2019 Yuxin Wang, Qiang Wang, Shaohuai Shi, Xin He, Zhenheng Tang, Kaiyong Zhao, Xiaowen Chu

Different from the existing end-to-end benchmarks which only present the training time, We try to investigate the impact of hardware, vendor's software library, and deep learning framework on the performance and energy consumption of AI training.


Symmetry-constrained Rectification Network for Scene Text Recognition

no code implementations ICCV 2019 MingKun Yang, Yushuo Guan, Minghui Liao, Xin He, Kaigui Bian, Song Bai, Cong Yao, Xiang Bai

Reading text in the wild is a very challenging task due to the diversity of text instances and the complexity of natural scenes.

Scene Text Recognition

AutoML: A Survey of the State-of-the-Art

2 code implementations2 Aug 2019 Xin He, Kaiyong Zhao, Xiaowen Chu

Deep learning (DL) techniques have penetrated all aspects of our lives and brought us great convenience.

Feature Engineering Hyperparameter Optimization +1

Simple Physical Adversarial Examples against End-to-End Autonomous Driving Models

no code implementations12 Mar 2019 Adith Boloor, Xin He, Christopher Gill, Yevgeniy Vorobeychik, Xuan Zhang

Recent advances in machine learning, especially techniques such as deep neural networks, are promoting a range of high-stakes applications, including autonomous driving, which often relies on deep learning for perception.

Autonomous Driving

Structure learning via unstructured kernel-based M-regression

no code implementations3 Jan 2019 Xin He, Yeheng Ge, Xingdong Feng

In statistical learning, identifying underlying structures of true target functions based on observed data plays a crucial role to facilitate subsequent modeling and analysis.

regression Sparse Learning +1

Scene Text Detection and Recognition: The Deep Learning Era

1 code implementation10 Nov 2018 Shangbang Long, Xin He, Cong Yao

As an important research area in computer vision, scene text detection and recognition has been inescapably influenced by this wave of revolution, consequentially entering the era of deep learning.

Scene Text Detection Text Detection

TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes

3 code implementations ECCV 2018 Shangbang Long, Jiaqiang Ruan, Wenjie Zhang, Xin He, Wenhao Wu, Cong Yao

Driven by deep neural networks and large scale datasets, scene text detection methods have progressed substantially over the past years, continuously refreshing the performance records on various standard benchmarks.

Curved Text Detection Text Detection

AxTrain: Hardware-Oriented Neural Network Training for Approximate Inference

no code implementations21 May 2018 Xin He, Liu Ke, Wenyan Lu, Guihai Yan, Xuan Zhang

The intrinsic error tolerance of neural network (NN) makes approximate computing a promising technique to improve the energy efficiency of NN inference.

Efficient kernel-based variable selection with sparsistency

no code implementations26 Feb 2018 Xin He, Junhui Wang, Shaogao Lv

Variable selection is central to high-dimensional data analysis, and various algorithms have been developed.

Variable Selection

Wilcoxon Rank-Based Tests for Clustered Data with R Package clusrank

no code implementations11 Jun 2017 Yujing Jiang, Xin He, Mei-Ling Ting Lee, Bernard Rosner, Jun Yan

For independent data, they are available in several R packages such as stats and coin.


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