Search Results for author: Song Guo

Found 53 papers, 7 papers with code

SFP: Spurious Feature-targeted Pruning for Out-of-Distribution Generalization

no code implementations19 May 2023 ingchun Wang, Jingcai Guo, Yi Liu, Song Guo, Weizhan Zhang, Xiangyong Cao, Qinghua Zheng

Based on the idea that in-distribution (ID) data with spurious features may have a lower experience risk, in this paper, we propose a novel Spurious Feature-targeted model Pruning framework, dubbed SFP, to automatically explore invariant substructures without referring to the above drawbacks.

Out-of-Distribution Generalization

CNS-Net: Conservative Novelty Synthesizing Network for Malware Recognition in an Open-set Scenario

no code implementations2 May 2023 Jingcai Guo, Song Guo, Shiheng Ma, Yuxia Sun, Yuanyuan Xu

Previous works usually assume the malware families are known to the classifier in a close-set scenario, i. e., testing families are the subset or at most identical to training families.

Open Set Learning

MDENet: Multi-modal Dual-embedding Networks for Malware Open-set Recognition

no code implementations2 May 2023 Jingcai Guo, Yuanyuan Xu, Wenchao Xu, Yufeng Zhan, Yuxia Sun, Song Guo

Malware open-set recognition (MOSR) aims at jointly classifying malware samples from known families and detect the ones from novel unknown families, respectively.

Open Set Learning

Towards Unbiased Training in Federated Open-world Semi-supervised Learning

no code implementations1 May 2023 Jie Zhang, Xiaosong Ma, Song Guo, Wenchao Xu

Federated Semi-supervised Learning (FedSSL) has emerged as a new paradigm for allowing distributed clients to collaboratively train a machine learning model over scarce labeled data and abundant unlabeled data.

Open-World Semi-Supervised Learning Transfer Learning

Offline-Online Class-incremental Continual Learning via Dual-prototype Self-augment and Refinement

no code implementations20 Mar 2023 Fushuo Huo, Wenchao Xu, Jingcai Guo, Haozhao Wang, Yunfeng Fan, Song Guo

In this paper, we propose a novel Dual-prototype Self-augment and Refinement method (DSR) for O$^2$CL problem, which consists of two strategies: 1) Dual class prototypes: Inner and hyper-dimensional prototypes are exploited to utilize the pre-trained information and obtain robust quasi-orthogonal representations rather than example buffers for both privacy preservation and memory reduction.

Continual Learning

DualMix: Unleashing the Potential of Data Augmentation for Online Class-Incremental Learning

no code implementations14 Mar 2023 Yunfeng Fan, Wenchao Xu, Haozhao Wang, Jiaqi Zhu, Junxiao Wang, Song Guo

Unfortunately, OCI learning can suffer from catastrophic forgetting (CF) as the decision boundaries for old classes can become inaccurate when perturbated by new ones.

class-incremental learning Class Incremental Learning +2

Towards Fairer and More Efficient Federated Learning via Multidimensional Personalized Edge Models

no code implementations9 Feb 2023 Yingchun Wang, Jingcai Guo, Jie Zhang, Song Guo, Weizhan Zhang, Qinghua Zheng

Federated learning (FL) is an emerging technique that trains massive and geographically distributed edge data while maintaining privacy.

Fairness Federated Learning

Data Quality-aware Mixed-precision Quantization via Hybrid Reinforcement Learning

no code implementations9 Feb 2023 Yingchun Wang, Jingcai Guo, Song Guo, Weizhan Zhang

Mixed-precision quantization mostly predetermines the model bit-width settings before actual training due to the non-differential bit-width sampling process, obtaining sub-optimal performance.

Quantization reinforcement-learning +1

(ML)$^2$P-Encoder: On Exploration of Channel-Class Correlation for Multi-Label Zero-Shot Learning

no code implementations CVPR 2023 Ziming Liu, Song Guo, Xiaocheng Lu, Jingcai Guo, Jiewei Zhang, Yue Zeng, Fushuo Huo

Recent studies usually approach multi-label zero-shot learning (MLZSL) with visual-semantic mapping on spatial-class correlation, which can be computationally costly, and worse still, fails to capture fine-grained class-specific semantics.

Multi-label zero-shot learning

Exploring Optimal Substructure for Out-of-distribution Generalization via Feature-targeted Model Pruning

no code implementations19 Dec 2022 Yingchun Wang, Jingcai Guo, Song Guo, Weizhan Zhang, Jie Zhang

Recent studies show that even highly biased dense networks contain an unbiased substructure that can achieve better out-of-distribution (OOD) generalization than the original model.

Out-of-Distribution Generalization

Efficient Stein Variational Inference for Reliable Distribution-lossless Network Pruning

no code implementations7 Dec 2022 Yingchun Wang, Song Guo, Jingcai Guo, Weizhan Zhang, Yida Xu, Jie Zhang, Yi Liu

Extensive experiments based on small Cifar-10 and large-scaled ImageNet demonstrate that our method can obtain sparser networks with great generalization performance while providing quantified reliability for the pruned model.

Network Pruning Variational Inference

Exploiting Personalized Invariance for Better Out-of-distribution Generalization in Federated Learning

no code implementations21 Nov 2022 Xueyang Tang, Song Guo, Jie Zhang

Recently, data heterogeneity among the training datasets on the local clients (a. k. a., Non-IID data) has attracted intense interest in Federated Learning (FL), and many personalized federated learning methods have been proposed to handle it.

Out-of-Distribution Generalization Personalized Federated Learning

ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learning

no code implementations19 Nov 2022 Fushuo Huo, Wenchao Xu, Song Guo, Jingcai Guo, Haozhao Wang, Ziming Liu

Open-World Compositional Zero-shot Learning (OW-CZSL) aims to recognize novel compositions of state and object primitives in images with no priors on the compositional space, which induces a tremendously large output space containing all possible state-object compositions.

Compositional Zero-Shot Learning

Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning

1 code implementation CVPR 2023 Xiaocheng Lu, Ziming Liu, Song Guo, Jingcai Guo

Existing methods either learn the combined state-object representation, challenging the generalization of unseen compositions, or design two classifiers to identify state and object separately from image features, ignoring the intrinsic relationship between them.

Compositional Zero-Shot Learning Novel Concepts

FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers

no code implementations15 Nov 2022 Jinyu Chen, Wenchao Xu, Song Guo, Junxiao Wang, Jie Zhang, Haozhao Wang

Federated Learning (FL) is an emerging paradigm that enables distributed users to collaboratively and iteratively train machine learning models without sharing their private data.

Federated Learning Language Modelling +1

CaDM: Codec-aware Diffusion Modeling for Neural-enhanced Video Streaming

no code implementations15 Nov 2022 Qihua Zhou, Ruibin Li, Song Guo, Peiran Dong, Yi Liu, Jingcai Guo, Zhenda Xu

Recent years have witnessed the dramatic growth of Internet video traffic, where the video bitstreams are often compressed and delivered in low quality to fit the streamer's uplink bandwidth.

Denoising Super-Resolution

PMR: Prototypical Modal Rebalance for Multimodal Learning

no code implementations CVPR 2023 Yunfeng Fan, Wenchao Xu, Haozhao Wang, Junxiao Wang, Song Guo

Multimodal learning (MML) aims to jointly exploit the common priors of different modalities to compensate for their inherent limitations.

Feature Correlation-guided Knowledge Transfer for Federated Self-supervised Learning

no code implementations14 Nov 2022 Yi Liu, Song Guo, Jie Zhang, Qihua Zhou, Yingchun Wang, Xiaohan Zhao

We prove that FedFoA is a model-agnostic training framework and can be easily compatible with state-of-the-art unsupervised FL methods.

Federated Learning Knowledge Distillation +3

Demystify Self-Attention in Vision Transformers from a Semantic Perspective: Analysis and Application

no code implementations13 Nov 2022 Leijie Wu, Song Guo, Yaohong Ding, Junxiao Wang, Wenchao Xu, Richard Yida Xu, Jie Zhang

In contrast, visual data exhibits a fundamentally different structure: Its basic unit (pixel) is a natural low-level representation with significant redundancies in the neighbourhood, which poses obvious challenges to the interpretability of MSA mechanism in ViT.

PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models -- Federated Learning in Age of Foundation Model

no code implementations24 Aug 2022 Tao Guo, Song Guo, Junxiao Wang, Wenchao Xu

Quick global aggregation of effective distributed parameters is crucial to federated learning (FL), which requires adequate bandwidth for parameters communication and sufficient user data for local training.

Federated Learning

Fed-FSNet: Mitigating Non-I.I.D. Federated Learning via Fuzzy Synthesizing Network

no code implementations21 Aug 2022 Jingcai Guo, Song Guo, Jie Zhang, Ziming Liu

Concretely, we maintain an edge-agnostic hidden model in the cloud server to estimate a less-accurate while direction-aware inversion of the global model.

Federated Learning Privacy Preserving

A Survey on Collaborative DNN Inference for Edge Intelligence

no code implementations16 Jul 2022 Weiqing Ren, Yuben Qu, Chao Dong, Yuqian Jing, Hao Sun, Qihui Wu, Song Guo

With the vigorous development of artificial intelligence (AI), the intelligent applications based on deep neural network (DNN) change people's lifestyles and the production efficiency.

A Survey on Gradient Inversion: Attacks, Defenses and Future Directions

no code implementations15 Jun 2022 Rui Zhang, Song Guo, Junxiao Wang, Xin Xie, DaCheng Tao

In particular, we dig out some critical ingredients from the iteration-based attacks, including data initialization, model training and gradient matching.

Accelerating Federated Learning via Sampling Anchor Clients with Large Batches

no code implementations13 Jun 2022 Feijie Wu, Song Guo, Zhihao Qu, Shiqi He, Ziming Liu

Clients in the miner group perform multiple local updates using serial mini-batches, and each local update is also indirectly regulated by the global target derived from the average of clients' bullseyes.

Federated Learning

CE-based white-box adversarial attacks will not work using super-fitting

no code implementations4 May 2022 Youhuan Yang, Lei Sun, Leyu Dai, Song Guo, Xiuqing Mao, Xiaoqin Wang, Bayi Xu

This is especially dangerous for some systems with high-security requirements, so this paper proposes a new defense method by using the model super-fitting state to improve the model's adversarial robustness (i. e., the accuracy under adversarial attacks).

Adversarial Attack Adversarial Robustness

Rethinking Classifier and Adversarial Attack

no code implementations4 May 2022 Youhuan Yang, Lei Sun, Leyu Dai, Song Guo, Xiuqing Mao, Xiaoqin Wang, Bayi Xu

Various defense models have been proposed to resist adversarial attack algorithms, but existing adversarial robustness evaluation methods always overestimate the adversarial robustness of these models (i. e., not approaching the lower bound of robustness).

Adversarial Attack Adversarial Robustness

Sign Bit is Enough: A Learning Synchronization Framework for Multi-hop All-reduce with Ultimate Compression

no code implementations14 Apr 2022 Feijie Wu, Shiqi He, Song Guo, Zhihao Qu, Haozhao Wang, Weihua Zhuang, Jie Zhang

Traditional one-bit compressed stochastic gradient descent can not be directly employed in multi-hop all-reduce, a widely adopted distributed training paradigm in network-intensive high-performance computing systems such as public clouds.

Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attention

no code implementations7 Mar 2022 Ziming Liu, Song Guo, Jingcai Guo, Yuanyuan Xu, Fushuo Huo

We argue that disregarding the connection between major and minor classes, i. e., correspond to the global and local information, respectively, is the cause of the problem.

Multi-label zero-shot learning

Efficient Attribute Unlearning: Towards Selective Removal of Input Attributes from Feature Representations

no code implementations27 Feb 2022 Tao Guo, Song Guo, Jiewei Zhang, Wenchao Xu, Junxiao Wang

Existing studies of machine unlearning mainly focus on sample-wise unlearning, such that a learnt model will not expose user's privacy at the sample level.

Face Recognition Fairness

A Coalition Formation Game Approach for Personalized Federated Learning

no code implementations5 Feb 2022 Leijie Wu, Song Guo, Yaohong Ding, Yufeng Zhan, Jie Zhang

Facing the challenge of statistical diversity in client local data distribution, personalized federated learning (PFL) has become a growing research hotspot.

Personalized Federated Learning

From Deterioration to Acceleration: A Calibration Approach to Rehabilitating Step Asynchronism in Federated Optimization

1 code implementation17 Dec 2021 Feijie Wu, Song Guo, Haozhao Wang, Zhihao Qu, Haobo Zhang, Jie Zhang, Ziming Liu

In the setting of federated optimization, where a global model is aggregated periodically, step asynchronism occurs when participants conduct model training by efficiently utilizing their computational resources.

Parameterized Knowledge Transfer for Personalized Federated Learning

1 code implementation NeurIPS 2021 Jie Zhang, Song Guo, Xiaosong Ma, Haozhao Wang, Wencao Xu, Feijie Wu

To deal with such model constraints, we exploit the potentials of heterogeneous model settings and propose a novel training framework to employ personalized models for different clients.

Personalized Federated Learning Transfer Learning

Federated Unlearning via Class-Discriminative Pruning

no code implementations22 Oct 2021 Junxiao Wang, Song Guo, Xin Xie, Heng Qi

Evaluated on CIFAR10 dataset, our method accelerates the speed of unlearning by 8. 9x for the ResNet model, and 7. 9x for the VGG model under no degradation in accuracy, compared to retraining from scratch.

Federated Learning Image Classification

SDN-based Resource Allocation in Edge and Cloud Computing Systems: An Evolutionary Stackelberg Differential Game Approach

no code implementations26 Sep 2021 Jun Du, Chunxiao Jiang, Abderrahim Benslimane, Song Guo, Yong Ren

Based on this dynamic access model, a Stackelberg differential game based cloud computing resource sharing mechanism is proposed to facilitate the resource trading between the cloud computing service provider (CCP) and different edge computing service providers (ECPs).

Edge-computing Management

Personalized Federated Learning with Contextualized Generalization

no code implementations24 Jun 2021 Xueyang Tang, Song Guo, Jingcai Guo

The prevalent personalized federated learning (PFL) usually pursues a trade-off between personalization and generalization by maintaining a shared global model to guide the training process of local models.

Personalized Federated Learning

Decentralized Federated Learning for UAV Networks: Architecture, Challenges, and Opportunities

no code implementations15 Apr 2021 Yuben Qu, Haipeng Dai, Yan Zhuang, Jiafa Chen, Chao Dong, Fan Wu, Song Guo

Unmanned aerial vehicles (UAVs), or say drones, are envisioned to support extensive applications in next-generation wireless networks in both civil and military fields.

Federated Learning

Online Multiple Object Tracking with Cross-Task Synergy

1 code implementation CVPR 2021 Song Guo, Jingya Wang, Xinchao Wang, DaCheng Tao

On the other hand, such reliable embeddings can boost identity-awareness through memory aggregation, hence strengthen attention modules and suppress drifts.

Multiple Object Tracking

DPN: Detail-Preserving Network with High Resolution Representation for Efficient Segmentation of Retinal Vessels

2 code implementations25 Sep 2020 Song Guo

2) The segmentation speed of DPN is over 20-160 times faster than other methods on the DRIVE dataset.

Scalable and Communication-efficient Decentralized Federated Edge Learning with Multi-blockchain Framework

no code implementations10 Aug 2020 Jiawen Kang, Zehui Xiong, Chunxiao Jiang, Yi Liu, Song Guo, Yang Zhang, Dusit Niyato, Cyril Leung, Chunyan Miao

This framework can achieve scalable and flexible decentralized FEL by individually manage local model updates or model sharing records for performance isolation.

Cryptography and Security

A Novel Perspective to Zero-shot Learning: Towards an Alignment of Manifold Structures via Semantic Feature Expansion

no code implementations30 Apr 2020 Jingcai Guo, Song Guo

One common practice in zero-shot learning is to train a projection between the visual and semantic feature spaces with labeled seen classes examples.

Zero-Shot Learning

Prophet: Proactive Candidate-Selection for Federated Learning by Predicting the Qualities of Training and Reporting Phases

no code implementations3 Feb 2020 Huawei Huang, Kangying Lin, Song Guo, Pan Zhou, Zibin Zheng

In the dynamic environment, the mobile devices selected by the existing reactive candidate-selection algorithms very possibly fail to complete the training and reporting phases of FL, because the FL parameter server only knows the currently-observed resources of all candidates.

Federated Learning

Intermittent Pulling with Local Compensation for Communication-Efficient Federated Learning

no code implementations22 Jan 2020 Haozhao Wang, Zhihao Qu, Song Guo, Xin Gao, Ruixuan Li, Baoliu Ye

A major bottleneck on the performance of distributed Stochastic Gradient Descent (SGD) algorithm for large-scale Federated Learning is the communication overhead on pushing local gradients and pulling global model.

BIG-bench Machine Learning Federated Learning

PIRATE: A Blockchain-based Secure Framework of Distributed Machine Learning in 5G Networks

no code implementations17 Dec 2019 Sicong Zhou, Huawei Huang, Wuhui Chen, Zibin Zheng, Song Guo

Therefore, to provide the byzantine-resilience for distributed learning in 5G era, this article proposes a secure computing framework based on the sharding-technique of blockchain, namely PIRATE.

Distributed, Parallel, and Cluster Computing Cryptography and Security

Deep Learning for Physical-Layer 5G Wireless Techniques: Opportunities, Challenges and Solutions

no code implementations21 Apr 2019 Hongji Huang, Song Guo, Guan Gui, Zhen Yang, Jianhua Zhang, Hikmet Sari, Fumiyuki Adachi

The new demands for high-reliability and ultra-high capacity wireless communication have led to extensive research into 5G communications.

Position-Aware Convolutional Networks for Traffic Prediction

no code implementations12 Apr 2019 Shiheng Ma, Jingcai Guo, Song Guo, Minyi Guo

Our approach employs the inception backbone network to capture rich features of traffic distribution on the whole area.

Management Traffic Prediction

MAANet: Multi-view Aware Attention Networks for Image Super-Resolution

1 code implementation12 Apr 2019 Jingcai Guo, Shiheng Ma, Song Guo

Specifically, we propose the local aware (LA) and global aware (GA) attention to deal with LR features in unequal manners, which can highlight the high-frequency components and discriminate each feature from LR images in the local and the global views, respectively.

Image Super-Resolution

Adaptive Adjustment with Semantic Feature Space for Zero-Shot Recognition

no code implementations30 Mar 2019 Jingcai Guo, Song Guo

To the best of our knowledge, our work is the first to consider the adaptive adjustment of semantic FS in ZSR.

Zero-Shot Learning

EE-AE: An Exclusivity Enhanced Unsupervised Feature Learning Approach

no code implementations30 Mar 2019 Jingcai Guo, Song Guo

In order to deal with this issue, we propose an Exclusivity Enhanced (EE) unsupervised feature learning approach to improve the conventional AE.

Gradient Scheduling with Global Momentum for Non-IID Data Distributed Asynchronous Training

no code implementations21 Feb 2019 Chengjie Li, Ruixuan Li, Haozhao Wang, Yuhua Li, Pan Zhou, Song Guo, Keqin Li

Distributed asynchronous offline training has received widespread attention in recent years because of its high performance on large-scale data and complex models.

Scheduling

BTS-DSN: Deeply Supervised Neural Network with Short Connections for Retinal Vessel Segmentation

1 code implementation11 Mar 2018 Song Guo, Kai Wang, Hong Kang, Yujun Zhang, Yingqi Gao, Tao Li

Results: The proposed BTS-DSN has been verified on DRIVE, STARE and CHASE_DB1 datasets, and showed competitive performance over other state-of-the-art methods.

Retinal Vessel Segmentation Specificity

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