Search Results for author: Xiaoxiao Li

Found 53 papers, 16 papers with code

Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients

1 code implementation7 Apr 2022 Nan Lu, Zhao Wang, Xiaoxiao Li, Gang Niu, Qi Dou, Masashi Sugiyama

We propose federation of unsupervised learning (FedUL), where the unlabeled data are transformed into surrogate labeled data for each of the clients, a modified model is trained by supervised FL, and the wanted model is recovered from the modified model.

Federated Learning

GATE: Graph CCA for Temporal SElf-supervised Learning for Label-efficient fMRI Analysis

no code implementations17 Mar 2022 Liang Peng, Nan Wang, Jie Xu, Xiaofeng Zhu, Xiaoxiao Li

To improve fMRI representation learning and classification under a label-efficient setting, we propose a novel and theory-driven self-supervised learning (SSL) framework on GCNs, namely Graph CCA for Temporal self-supervised learning on fMRI analysis GATE.

Classification Representation Learning +1

Evaluating Explainable AI on a Multi-Modal Medical Imaging Task: Can Existing Algorithms Fulfill Clinical Requirements?

no code implementations12 Mar 2022 Weina Jin, Xiaoxiao Li, Ghassan Hamarneh

The evaluation and MSFI metric can guide the design and selection of XAI algorithms to meet clinical requirements on multi-modal explanation.

Feature Importance

Guidelines and evaluation for clinical explainable AI on medical image analysis

1 code implementation16 Feb 2022 Weina Jin, Xiaoxiao Li, Mostafa Fatehi, Ghassan Hamarneh

To bridge the research gap, we propose the Clinical XAI Guidelines that consist of five criteria a clinical XAI needs to be optimized for.

Explainable artificial intelligence

RestoreDet: Degradation Equivariant Representation for Object Detection in Low Resolution Images

no code implementations7 Jan 2022 Ziteng Cui, Yingying Zhu, Lin Gu, Guo-Jun Qi, Xiaoxiao Li, Peng Gao, Zenghui Zhang, Tatsuya Harada

Image restoration algorithms such as super resolution (SR) are indispensable pre-processing modules for object detection in degraded images.

Image Restoration Object Detection +2

Leveraging Human Selective Attention for Medical Image Analysis with Limited Training Data

no code implementations2 Dec 2021 Yifei HUANG, Xiaoxiao Li, Lijin Yang, Lin Gu, Yingying Zhu, Hirofumi Seo, Qiuming Meng, Tatsuya Harada, Yoichi Sato

Then we design a novel Auxiliary Attention Block (AAB) to allow information from SAN to be utilized by the backbone encoder to focus on selective areas.

Tumor Segmentation

SCaLa: Supervised Contrastive Learning for End-to-End Speech Recognition

no code implementations8 Oct 2021 Li Fu, Xiaoxiao Li, Runyu Wang, Lu Fan, Zhengchen Zhang, Meng Chen, Youzheng Wu, Xiaodong He

End-to-end Automatic Speech Recognition (ASR) models are usually trained to optimize the loss of the whole token sequence, while neglecting explicit phonemic-granularity supervision.

Automatic Speech Recognition Contrastive Learning +1

Provable Federated Adversarial Learning via Min-max Optimization

no code implementations29 Sep 2021 Xiaoxiao Li, Zhao Song, Jiaming Yang

Unlike the convergence analysis in centralized training that relies on the gradient direction, it is significantly harder to analyze the convergence in FAL for two reasons: 1) the complexity of min-max optimization, and 2) model not updating in the gradient direction due to the multi-local updates on the client-side before aggregation.

Federated Learning

Unsupervised Federated Learning is Possible

no code implementations ICLR 2022 Nan Lu, Zhao Wang, Xiaoxiao Li, Gang Niu, Qi Dou, Masashi Sugiyama

We propose federation of unsupervised learning (FedUL), where the unlabeled data are transformed into surrogate labeled data for each of the clients, a modified model is trained by supervised FL, and the wanted model is recovered from the modified model.

Federated Learning

On the Fairness of Swarm Learning in Skin Lesion Classification

no code implementations24 Sep 2021 Di Fan, Yifan Wu, Xiaoxiao Li

Distributed and collaborative learning is an approach to involve training models in massive, heterogeneous, and distributed data sources, also known as nodes.

Classification Edge-computing +3

EMA: Auditing Data Removal from Trained Models

1 code implementation8 Sep 2021 Yangsibo Huang, Xiaoxiao Li, Kai Li

In this paper, we propose a new method called Ensembled Membership Auditing (EMA) for auditing data removal to overcome these limitations.

Subgraph Federated Learning with Missing Neighbor Generation

no code implementations NeurIPS 2021 Ke Zhang, Carl Yang, Xiaoxiao Li, Lichao Sun, Siu Ming Yiu

Graphs have been widely used in data mining and machine learning due to their unique representation of real-world objects and their interactions.

Federated Learning Graph Mining

FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Convergence Analysis

no code implementations11 May 2021 Baihe Huang, Xiaoxiao Li, Zhao Song, Xin Yang

Nevertheless, training analysis of neural networks in FL is non-trivial for two reasons: first, the objective loss function we are optimizing is non-smooth and non-convex, and second, we are even not updating in the gradient direction.

Federated Learning

Demographic-Guided Attention in Recurrent Neural Networks for Modeling Neuropathophysiological Heterogeneity

no code implementations15 Apr 2021 Nicha C. Dvornek, Xiaoxiao Li, Juntang Zhuang, Pamela Ventola, James S. Duncan

Heterogeneous presentation of a neurological disorder suggests potential differences in the underlying pathophysiological changes that occur in the brain.

Time Series

Estimating and Improving Fairness with Adversarial Learning

no code implementations7 Mar 2021 Xiaoxiao Li, Ziteng Cui, Yifan Wu, Lin Gu, Tatsuya Harada

To tackle this issue, we propose an adversarial multi-task training strategy to simultaneously mitigate and detect bias in the deep learning-based medical image analysis system.


FedBN: Federated Learning on Non-IID Features via Local Batch Normalization

3 code implementations ICLR 2021 Xiaoxiao Li, Meirui Jiang, Xiaofei Zhang, Michael Kamp, Qi Dou

The emerging paradigm of federated learning (FL) strives to enable collaborative training of deep models on the network edge without centrally aggregating raw data and hence improving data privacy.

Autonomous Driving Federated Learning

What Can Phase Retrieval Tell Us About Private Distributed Learning?

no code implementations ICLR 2021 Sitan Chen, Xiaoxiao Li, Zhao Song, Danyang Zhuo

In this work, we examine the security of InstaHide, a scheme recently proposed by \cite{hsla20} for preserving the security of private datasets in the context of distributed learning.

Automating Document Classification with Distant Supervision to Increase the Efficiency of Systematic Reviews

no code implementations9 Dec 2020 Xiaoxiao Li, Rabah Al-Zaidy, Amy Zhang, Stefan Baral, Le Bao, C. Lee Giles

Conclusions: In sum, the automated procedure of document classification presented here could improve both the precision and efficiency of systematic reviews, as well as facilitating live reviews, where reviews are updated regularly.

Document Classification General Classification

On InstaHide, Phase Retrieval, and Sparse Matrix Factorization

no code implementations23 Nov 2020 Sitan Chen, Xiaoxiao Li, Zhao Song, Danyang Zhuo

In this work, we examine the security of InstaHide, a scheme recently proposed by [Huang, Song, Li and Arora, ICML'20] for preserving the security of private datasets in the context of distributed learning.

MixCon: Adjusting the Separability of Data Representations for Harder Data Recovery

no code implementations22 Oct 2020 Xiaoxiao Li, Yangsibo Huang, Binghui Peng, Zhao Song, Kai Li

To address the issue that deep neural networks (DNNs) are vulnerable to model inversion attacks, we design an objective function, which adjusts the separability of the hidden data representations, as a way to control the trade-off between data utility and vulnerability to inversion attacks.

Texture Memory-Augmented Deep Patch-Based Image Inpainting

1 code implementation28 Sep 2020 Rui Xu, Minghao Guo, Jiaqi Wang, Xiaoxiao Li, Bolei Zhou, Chen Change Loy

By bringing together the best of both paradigms, we propose a new deep inpainting framework where texture generation is guided by a texture memory of patch samples extracted from unmasked regions.

Image Inpainting Texture Synthesis

Pooling Regularized Graph Neural Network for fMRI Biomarker Analysis

no code implementations29 Jul 2020 Xiaoxiao Li, Yuan Zhou, Nicha C. Dvornek, Muhan Zhang, Juntang Zhuang, Pamela Ventola, James S. Duncan

We propose an interpretable GNN framework with a novel salient region selection mechanism to determine neurological brain biomarkers associated with disorders.

Knowledge Distillation Meets Self-Supervision

2 code implementations ECCV 2020 Guodong Xu, Ziwei Liu, Xiaoxiao Li, Chen Change Loy

Knowledge distillation, which involves extracting the "dark knowledge" from a teacher network to guide the learning of a student network, has emerged as an important technique for model compression and transfer learning.

Contrastive Learning Knowledge Distillation +2

Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODE

2 code implementations ICML 2020 Juntang Zhuang, Nicha Dvornek, Xiaoxiao Li, Sekhar Tatikonda, Xenophon Papademetris, James Duncan

Neural ordinary differential equations (NODEs) have recently attracted increasing attention; however, their empirical performance on benchmark tasks (e. g. image classification) are significantly inferior to discrete-layer models.

General Classification Image Classification +1

On the number of frequency hypercubes $F^n(4;2,2)$

no code implementations21 May 2020 Minjia Shi, Shukai Wang, Xiaoxiao Li, Denis S. Krotov

A frequency $n$-cube $F^n(4;2, 2)$ is an $n$-dimensional $4$-by-...-by-$4$ array filled by $0$s and $1$s such that each line contains exactly two $1$s.

Combinatorics Discrete Mathematics 05B15

Visual Perception Model for Rapid and Adaptive Low-light Image Enhancement

1 code implementation15 May 2020 Xiaoxiao Li, Xiaopeng Guo, Liye Mei, Mingyu Shang, Jie Gao, Maojing Shu, Xiang Wang

The core of VP model is to decompose the light source into light intensity and light spatial distribution to describe the perception process of HVS, offering refinement estimation of illumination and reflectance.

Low-Light Image Enhancement

Incremental Learning for End-to-End Automatic Speech Recognition

no code implementations11 May 2020 Li Fu, Xiaoxiao Li, Libo Zi, Zhengchen Zhang, Youzheng Wu, Xiaodong He, BoWen Zhou

In this paper, we propose an incremental learning method for end-to-end Automatic Speech Recognition (ASR) which enables an ASR system to perform well on new tasks while maintaining the performance on its originally learned ones.

Automatic Speech Recognition Incremental Learning +1

Research on Modeling Units of Transformer Transducer for Mandarin Speech Recognition

no code implementations26 Apr 2020 Li Fu, Xiaoxiao Li, Libo Zi

To improve the performance of RNN-T for Mandarin speech recognition task, a novel transformer transducer with the combination architecture of self-attention transformer and RNN is proposed.

Speech Recognition

Explain Graph Neural Networks to Understand Weighted Graph Features in Node Classification

no code implementations2 Feb 2020 Xiaoxiao Li, Joao Saude

GNNs combine node features, connection patterns, and graph structure by using a neural network to embed node information and pass it through edges in the graph.

General Classification Node Classification

Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation: ABIDE Results

1 code implementation16 Jan 2020 Xiaoxiao Li, Yufeng Gu, Nicha Dvornek, Lawrence Staib, Pamela Ventola, James S. Duncan

However, to effectively train a high-quality deep learning model, the aggregation of a significant amount of patient information is required.

Domain Adaptation Federated Learning

Jointly Discriminative and Generative Recurrent Neural Networks for Learning from fMRI

no code implementations15 Oct 2019 Nicha C. Dvornek, Xiaoxiao Li, Juntang Zhuang, James S. Duncan

The addition of the generative model constrains the network to learn functional communities represented by the LSTM nodes that are both consistent with the data generation as well as useful for the classification task.

Classification General Classification +1

Decision Explanation and Feature Importance for Invertible Networks

1 code implementation30 Sep 2019 Juntang Zhuang, Nicha C. Dvornek, Xiaoxiao Li, Junlin Yang, James S. Duncan

We can determine the decision boundary of a linear classifier in the feature space; since the transform is invertible, we can invert the decision boundary from the feature space to the input space.

Feature Importance

Ordinary differential equations on graph networks

no code implementations25 Sep 2019 Juntang Zhuang, Nicha Dvornek, Xiaoxiao Li, James S. Duncan

Inspired by neural ordinary differential equation (NODE) for data in the Euclidean domain, we extend the idea of continuous-depth models to graph data, and propose graph ordinary differential equation (GODE).

Graph Classification Node Classification

Graph Embedding Using Infomax for ASD Classification and Brain Functional Difference Detection

no code implementations9 Aug 2019 Xiaoxiao Li, Nicha C. Dvornek, Juntang Zhuang, Pamela Ventola, James Duncan

Here, we model the whole brain fMRI as a graph, which preserves geometrical and temporal information and use a Graph Neural Network (GNN) to learn from the graph-structured fMRI data.

Classification General Classification +1

Deep Flow-Guided Video Inpainting

2 code implementations CVPR 2019 Rui Xu, Xiaoxiao Li, Bolei Zhou, Chen Change Loy

Then the synthesized flow field is used to guide the propagation of pixels to fill up the missing regions in the video.

Frame One-shot visual object segmentation +3

Hybrid Task Cascade for Instance Segmentation

5 code implementations CVPR 2019 Kai Chen, Jiangmiao Pang, Jiaqi Wang, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jianping Shi, Wanli Ouyang, Chen Change Loy, Dahua Lin

In exploring a more effective approach, we find that the key to a successful instance segmentation cascade is to fully leverage the reciprocal relationship between detection and segmentation.

Instance Segmentation Object Detection +1

Efficient Interpretation of Deep Learning Models Using Graph Structure and Cooperative Game Theory: Application to ASD Biomarker Discovery

no code implementations14 Dec 2018 Xiaoxiao Li, Nicha C. Dvornek, Yuan Zhou, Juntang Zhuang, Pamela Ventola, James S. Duncan

Cooperative game theory is advantageous here because it directly considers the interaction between features and can be applied to any machine learning method, making it a novel, more accurate way of determining instance-wise biomarker importance from deep learning models.

Feature Importance

Repetitive Motion Estimation Network: Recover cardiac and respiratory signal from thoracic imaging

no code implementations8 Nov 2018 Xiaoxiao Li, Vivek Singh, Yifan Wu, Klaus Kirchberg, James Duncan, Ankur Kapoor

Tracking organ motion is important in image-guided interventions, but motion annotations are not always easily available.

Motion Estimation

What evidence does deep learning model use to classify Skin Lesions?

no code implementations2 Nov 2018 Xiaoxiao Li, Junyan Wu, Eric Z. Chen, Hongda Jiang

In this paper, we propose a method to interpret the deep learning classification findings.

Decision Making

Brain Biomarker Interpretation in ASD Using Deep Learning and fMRI

no code implementations23 Aug 2018 Xiaoxiao Li, Nicha C. Dvornek, Juntang Zhuang, Pamela Ventola, James S. Duncan

Therefore, in this work, we address the problem of interpreting reliable biomarkers associated with identifying ASD; specifically, we propose a 2-stage method that classifies ASD and control subjects using fMRI images and interprets the saliency features activated by the classifier.

Decision Making

Video Object Segmentation with Re-identification

3 code implementations1 Aug 2017 Xiaoxiao Li, Yuankai Qi, Zhe Wang, Kai Chen, Ziwei Liu, Jianping Shi, Ping Luo, Xiaoou Tang, Chen Change Loy

Specifically, our Video Object Segmentation with Re-identification (VS-ReID) model includes a mask propagation module and a ReID module.

Semantic Segmentation Video Object Segmentation +2

Semantic Image Segmentation via Deep Parsing Network

no code implementations ICCV 2015 Ziwei Liu, Xiaoxiao Li, Ping Luo, Chen Change Loy, Xiaoou Tang

This paper addresses semantic image segmentation by incorporating rich information into Markov Random Field (MRF), including high-order relations and mixture of label contexts.

Semantic Segmentation

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