Search Results for author:
Found 100 papers, 42 papers with code
Intelligent Agents for Auction-based Federated Learning: A Survey
To enhance the efficiency in AFL decision support for stakeholders (i. e., data consumers, data owners, and the auctioneer), intelligent agent-based techniques have emerged.
Injecting New Knowledge into Large Language Models via Supervised Fine-Tuning
We present a novel dataset generation process that leads to more effective knowledge ingestion through SFT, and our results show considerable performance improvements in Q&A tasks related to out-of-domain knowledge.
Learnable Community-Aware Transformer for Brain Connectome Analysis with Token Clustering
Neuroscientific research has revealed that the complex brain network can be organized into distinct functional communities, each characterized by a cohesive group of regions of interest (ROIs) with strong interconnections.
Universal Debiased Editing on Foundation Models for Fair Medical Image Classification
UDE is capable of mitigating bias both within the FM API embedding and the images themselves.
OpenMEDLab: An Open-source Platform for Multi-modality Foundation Models in Medicine
The emerging trend of advancing generalist artificial intelligence, such as GPTv4 and Gemini, has reshaped the landscape of research (academia and industry) in machine learning and many other research areas.
Content Conditional Debiasing for Fair Text Embedding
We achieve fairness while maintaining utility trade-off by ensuring conditional independence between sensitive attributes and text embeddings conditioned on the content.
pFedMoE: Data-Level Personalization with Mixture of Experts for Model-Heterogeneous Personalized Federated Learning
It assigns a shared homogeneous small feature extractor and a local gating network for each client's local heterogeneous large model.
Backdoor Attack on Unpaired Medical Image-Text Foundation Models: A Pilot Study on MedCLIP
Notably, MedCLIP, a vision-language contrastive learning-based medical FM, has been designed using unpaired image-text training.
MMGPL: Multimodal Medical Data Analysis with Graph Prompt Learning
Nonetheless, applying existing prompt learning methods for the diagnosis of neurological disorder still suffers from two issues: (i) existing methods typically treat all patches equally, despite the fact that only a small number of patches in neuroimaging are relevant to the disease, and (ii) they ignore the structural information inherent in the brain connection network which is crucial for understanding and diagnosing neurological disorders.
FedSSA: Semantic Similarity-based Aggregation for Efficient Model-Heterogeneous Personalized Federated Learning
Existing MHPFL approaches often rely on a public dataset with the same nature as the learning task, or incur high computation and communication costs.
Learning High-Order Relationships of Brain Regions
In response to this gap, we propose a novel method named HYBRID which aims to extract MIMR high-order relationships from fMRI data.
Heteroscedastic Uncertainty Estimation for Probabilistic Unsupervised Registration of Noisy Medical Images
This paper proposes a heteroscedastic uncertainty estimation framework for unsupervised medical image registration.
Energizing Federated Learning via Filter-Aware Attention
Federated learning (FL) is a promising distributed paradigm, eliminating the need for data sharing but facing challenges from data heterogeneity.
A Survey of Federated Unlearning: A Taxonomy, Challenges and Future Directions
Achieving an optimal equilibrium among these facets is crucial for maintaining the effectiveness and usability of FL systems while adhering to privacy and security standards.
Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning
Existing Generalized FL (GFL) and Personalized FL (PFL) methods have limitations in balancing performance across both global and local data distributions.
pFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuning
Federated learning (FL) is an emerging machine learning paradigm in which a central server coordinates multiple participants (clients) collaboratively to train on decentralized data.
Client-Level Differential Privacy via Adaptive Intermediary in Federated Medical Imaging
In this paper, we propose to optimize the trade-off under the context of client-level DP, which focuses on privacy during communications.
Transsion TSUP's speech recognition system for ASRU 2023 MADASR Challenge
The system focuses on adapting ASR models for low-resource Indian languages and covers all four tracks of the challenge.
FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation
In this paper, we propose a novel federated model soup method (i. e., selective interpolation of model parameters) to optimize the trade-off between local and global performance.
Community-Aware Transformer for Autism Prediction in fMRI Connectome
Investigating functional magnetic resonance imaging (fMRI)-based brain functional connectome can aid in the understanding and diagnosis of ASD, leading to more effective treatments.
Stability and Fluctuations in Complex Ecological Systems
From 08-12 August, 2022, 32 individuals participated in a workshop, Stability and Fluctuations in Complex Ecological Systems, at the Lorentz Center, located in Leiden, The Netherlands.
LESS: Label-efficient Multi-scale Learning for Cytological Whole Slide Image Screening
We provide appropriate supervision by using slide-level labels to improve the learning of patch-level features.
Forgettable Federated Linear Learning with Certified Data Removal
To this end, we propose the Forgettable Federated Linear Learning (2F2L) framework featured with novel training and data removal strategies.
Scalable Data Point Valuation in Decentralized Learning
The valuation of data points through DDVal allows to also draw hierarchical conclusions on the contribution of institutions, and we empirically show that the accuracy of DDVal in estimating institutional contributions is higher than existing Shapley value approximation methods for federated learning.
Matching-based Data Valuation for Generative Model
To the best of their knowledge, GMValuator is the first work that offers a training-free, post-hoc data valuation strategy for deep generative models.
Biological Factor Regulatory Neural Network
BFReg-NN starts from gene expression data and is capable of merging most existing biological knowledge into the model, including the regulatory relations among genes or proteins (e. g., gene regulatory networks (GRN), protein-protein interaction networks (PPI)) and the hierarchical relations among genes, proteins and pathways (e. g., several genes/proteins are contained in a pathway).
The XAI Alignment Problem: Rethinking How Should We Evaluate Human-Centered AI Explainability Techniques
Optimizing XAI for plausibility regardless of the model decision correctness also jeopardizes model trustworthiness, because doing so breaks an important assumption in human-human explanation that plausible explanations typically imply correct decisions, and vice versa; and violating this assumption eventually leads to either undertrust or overtrust of AI models.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+1
Federated Virtual Learning on Heterogeneous Data with Local-global Distillation
To address this, we propose a new method, called Federated Virtual Learning on Heterogeneous Data with Local-Global Distillation (FedLGD), which trains FL using a smaller synthetic dataset (referred as virtual data) created through a combination of local and global dataset distillation.
Differentially Private Neural Tangent Kernels for Privacy-Preserving Data Generation
Maximum mean discrepancy (MMD) is a particularly useful distance metric for differentially private data generation: when used with finite-dimensional features it allows us to summarize and privatize the data distribution once, which we can repeatedly use during generator training without further privacy loss.
On Fairness of Medical Image Classification with Multiple Sensitive Attributes via Learning Orthogonal Representations
In this paper, we propose a novel method for fair representation learning with respect to multi-sensitive attributes.
SADM: Sequence-Aware Diffusion Model for Longitudinal Medical Image Generation
To this end, we propose a sequence-aware diffusion model (SADM) for the generation of longitudinal medical images.
Robust Split Federated Learning for U-shaped Medical Image Networks
To achieve this goal, in this paper, we propose Robust Split Federated Learning (RoS-FL) for U-shaped medical image networks, which is a novel hybrid learning paradigm of FL and SL.
A Convergence Theory for Federated Average: Beyond Smoothness
As a leading algorithm in this setting, Federated Average FedAvg, which runs Stochastic Gradient Descent (SGD) in parallel on local devices and averages the sequences only once in a while, have been widely used due to their simplicity and low communication cost.
Improving Fairness in Image Classification via Sketching
Fairness is a fundamental requirement for trustworthy and human-centered Artificial Intelligence (AI) system.
Backdoor Attack and Defense in Federated Generative Adversarial Network-based Medical Image Synthesis
However, given that the FL server cannot access the raw data, it is vulnerable to backdoor attacks, an adversarial by poisoning training data.
FedMT: Federated Learning with Mixed-type Labels
In federated learning (FL), classifiers (e. g., deep networks) are trained on datasets from multiple data centers without exchanging data across them, which improves the sample efficiency.
Efficient Medical Image Assessment via Self-supervised Learning
Existing data assessment methods commonly require knowing the labels in advance, which are not feasible to achieve our goal of 'knowing which data to label.'
Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labels
Blindly leveraging all pixels in training hence can lead to the data imbalance issues, and cause deteriorated performance; (2) consistency: it remains unclear whether a segmentation model has learned meaningful and yet consistent anatomical features due to the intra-class variations between different anatomical features; and (3) diversity: the intra-slice correlations within the entire dataset have received significantly less attention.
Transcending XAI Algorithm Boundaries through End-User-Inspired Design
The boundaries of existing explainable artificial intelligence (XAI) algorithms are confined to problems grounded in technical users' demand for explainability.
Federated Adversarial Learning: A Framework with Convergence Analysis
Unlike the convergence analysis in classical centralized training that relies on the gradient direction, it is significantly harder to analyze the convergence in FAL for three reasons: 1) the complexity of min-max optimization, 2) model not updating in the gradient direction due to the multi-local updates on the client-side before aggregation and 3) inter-client heterogeneity.
Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection
Image restoration algorithms such as super resolution (SR) are indispensable pre-processing modules for object detection in low quality images.
Backdoor Attack is a Devil in Federated GAN-based Medical Image Synthesis
In this study, we propose a way of attacking federated GAN (FedGAN) by treating the discriminator with a commonly used data poisoning strategy in backdoor attack classification models.
Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysis
Mapping the connections of the human brain as a network is one of the most pervasive paradigms in neuroscience.
Dynamic Bank Learning for Semi-supervised Federated Image Diagnosis with Class Imbalance
Despite recent progress on semi-supervised federated learning (FL) for medical image diagnosis, the problem of imbalanced class distributions among unlabeled clients is still unsolved for real-world use.
Class Impression for Data-free Incremental Learning
Here, we propose a novel data-free class incremental learning framework that first synthesizes data from the model trained on previous classes to generate a \ours.
Hypernetwork-based Personalized Federated Learning for Multi-Institutional CT Imaging
The basic assumption of HyperFed is that the optimization problem for each institution can be divided into two parts: the local data adaption problem and the global CT imaging problem, which are implemented by an institution-specific hypernetwork and a global-sharing imaging network, respectively.
MISSU: 3D Medical Image Segmentation via Self-distilling TransUNet
U-Nets have achieved tremendous success in medical image segmentation.
Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients
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.
GATE: Graph CCA for Temporal SElf-supervised Learning for Label-efficient fMRI Analysis
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.
Evaluating Explainable AI on a Multi-Modal Medical Imaging Task: Can Existing Algorithms Fulfill Clinical Requirements?
The evaluation and MSFI metric can guide the design and selection of XAI algorithms to meet clinical requirements on multi-modal explanation.
Explainable Artificial Intelligence (XAI)
Feature Importance
Guidelines and Evaluation of Clinical Explainable AI in Medical Image Analysis
Following the guidelines, we conducted a systematic evaluation on a novel problem of multi-modal medical image explanation with two clinical tasks, and proposed new evaluation metrics accordingly.
Computational Efficiency
Explainable artificial intelligence
+1
RestoreDet: Degradation Equivariant Representation for Object Detection in Low Resolution Images
Image restoration algorithms such as super resolution (SR) are indispensable pre-processing modules for object detection in degraded images.
FedNI: Federated Graph Learning with Network Inpainting for Population-Based Disease Prediction
Then we train a global GCN node classifier across institutions using a federated graph learning platform.
Leveraging Human Selective Attention for Medical Image Analysis with Limited Training Data
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.
UniFed: A Unified Framework for Federated Learning on Non-IID Image Features
In this work, we propose a unified framework to tackle the non-iid issues for internal and external clients together.
SCaLa: Supervised Contrastive Learning for End-to-End Speech Recognition
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
Automatic Speech Recognition (ASR)
+3
Provable Federated Adversarial Learning via Min-max Optimization
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.
Unsupervised Federated Learning is Possible
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.
On the Fairness of Swarm Learning in Skin Lesion Classification
Distributed and collaborative learning is an approach to involve training models in massive, heterogeneous, and distributed data sources, also known as nodes.
EMA: Auditing Data Removal from Trained Models
In this paper, we propose a new method called Ensembled Membership Auditing (EMA) for auditing data removal to overcome these limitations.
BrainNNExplainer: An Interpretable Graph Neural Network Framework for Brain Network based Disease Analysis
Interpretable brain network models for disease prediction are of great value for the advancement of neuroscience.
One Map Does Not Fit All: Evaluating Saliency Map Explanation on Multi-Modal Medical Images
The maps highlight important features for AI model's prediction.
Subgraph Federated Learning with Missing Neighbor Generation
Graphs have been widely used in data mining and machine learning due to their unique representation of real-world objects and their interactions.
FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Convergence Analysis
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.
Demographic-Guided Attention in Recurrent Neural Networks for Modeling Neuropathophysiological Heterogeneity
Heterogeneous presentation of a neurological disorder suggests potential differences in the underlying pathophysiological changes that occur in the brain.
Estimating and Improving Fairness with Adversarial Learning
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
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.
What Can Phase Retrieval Tell Us About Private Distributed Learning?
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
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.
On InstaHide, Phase Retrieval, and Sparse Matrix Factorization
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
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
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.
Pooling Regularized Graph Neural Network for fMRI Biomarker Analysis
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
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.
Ranked #32 on
Knowledge Distillation
on ImageNet
Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODE
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.
On the number of frequency hypercubes $F^n(4;2,2)$
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
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.
Incremental Learning for End-to-End Automatic Speech Recognition
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
Automatic Speech Recognition (ASR)
+3
Research on Modeling Units of Transformer Transducer for Mandarin Speech Recognition
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.
Explain Graph Neural Networks to Understand Weighted Graph Features in Node Classification
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.
Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation: ABIDE Results
However, to effectively train a high-quality deep learning model, the aggregation of a significant amount of patient information is required.
Jointly Discriminative and Generative Recurrent Neural Networks for Learning from fMRI
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.
REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs
As part of REFUGE, we have publicly released a data set of 1200 fundus images with ground truth segmentations and clinical glaucoma labels, currently the largest existing one.
Decision Explanation and Feature Importance for Invertible Networks
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.
Ordinary differential equations on graph networks
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 Embedding Using Infomax for ASD Classification and Brain Functional Difference Detection
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.
Invertible Network for Classification and Biomarker Selection for ASD
Recently deep learning methods have achieved success in the classification task of ASD using fMRI data.
Graph Neural Network for Interpreting Task-fMRI Biomarkers
Our pipeline can be generalized to other graph feature importance interpretation problems.
MMDetection: Open MMLab Detection Toolbox and Benchmark
In this paper, we introduce the various features of this toolbox.
Deep Flow-Guided Video Inpainting
Then the synthesized flow field is used to guide the propagation of pixels to fill up the missing regions in the video.
Ranked #8 on
Video Inpainting
on DAVIS
One-shot visual object segmentation
Optical Flow Estimation
+2
Hybrid Task Cascade for Instance Segmentation
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.
Ranked #32 on
Object Detection
on COCO-O
Efficient Interpretation of Deep Learning Models Using Graph Structure and Cooperative Game Theory: Application to ASD Biomarker Discovery
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.
Repetitive Motion Estimation Network: Recover cardiac and respiratory signal from thoracic imaging
Tracking organ motion is important in image-guided interventions, but motion annotations are not always easily available.
What evidence does deep learning model use to classify Skin Lesions?
In this paper, we propose a method to interpret the deep learning classification findings.
Brain Biomarker Interpretation in ASD Using Deep Learning and fMRI
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.
Video Object Segmentation with Joint Re-identification and Attention-Aware Mask Propagation
The problem of video object segmentation can become extremely challenging when multiple instances co-exist.
Video Object Segmentation with Re-identification
Specifically, our Video Object Segmentation with Re-identification (VS-ReID) model includes a mask propagation module and a ReID module.
Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade
Third, in comparison to MC, LC is an end-to-end trainable framework, allowing joint learning of all sub-models.
Ranked #22 on
Semantic Segmentation
on PASCAL VOC 2012 test
Deep Learning Markov Random Field for Semantic Segmentation
Semantic segmentation tasks can be well modeled by Markov Random Field (MRF).
Semantic Image Segmentation via Deep Parsing Network
This paper addresses semantic image segmentation by incorporating rich information into Markov Random Field (MRF), including high-order relations and mixture of label contexts.
Ranked #89 on
Semantic Segmentation
on Cityscapes test
