Search Results for author:
Found 57 papers, 12 papers with code
ActPerFL: Active Personalized Federated Learning
Inspired by Bayesian hierarchical models, we develop ActPerFL, a self-aware personalized FL method where each client can automatically balance the training of its local personal model and the global model that implicitly contributes to other clients’ training.
RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees
Subsequently, we employ a classifier that is jointly trained with the watermark to detect the presence of the watermark.
Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety.
A Graph Transformer-Driven Approach for Network Robustness Learning
Learning and analysis of network robustness, including controllability robustness and connectivity robustness, is critical for various networked systems against attacks.
A Framework for Incentivized Collaborative Learning
Collaborations among various entities, such as companies, research labs, AI agents, and edge devices, have become increasingly crucial for achieving machine learning tasks that cannot be accomplished by a single entity alone.
Semi-Supervised Federated Learning for Keyword Spotting
Keyword Spotting (KWS) is a critical aspect of audio-based applications on mobile devices and virtual assistants.
Provable Identifiability of Two-Layer ReLU Neural Networks via LASSO Regularization
In this paper, the territory of LASSO is extended to two-layer ReLU neural networks, a fashionable and powerful nonlinear regression model.
Federated Alternate Training (FAT): Leveraging Unannotated Data Silos in Federated Segmentation for Medical Imaging
It is a distributed learning framework naturally suitable for privacy-sensitive medical imaging datasets.
PI-FL: Personalized and Incentivized Federated Learning
Personalized FL has been widely used to cater to heterogeneity challenges with non-IID data.
Pruning Deep Neural Networks from a Sparsity Perspective
Our extensive experiments corroborate the hypothesis that for a generic pruning procedure, PQI decreases first when a large model is being effectively regularized and then increases when its compressibility reaches a limit that appears to correspond to the beginning of underfitting.
Quickest Change Detection for Unnormalized Statistical Models
This paper develops a new variant of the classical Cumulative Sum (CUSUM) algorithm for the quickest change detection.
Personalized Federated Recommender Systems with Private and Partially Federated AutoEncoders
Recommender Systems (RSs) have become increasingly important in many application domains, such as digital marketing.
A Framework for Understanding Model Extraction Attack and Defense
The privacy of machine learning models has become a significant concern in many emerging Machine-Learning-as-a-Service applications, where prediction services based on well-trained models are offered to users via pay-per-query.
A Theoretical Understanding of Neural Network Compression from Sparse Linear Approximation
One problem is understanding if a network is more compressible than another of the same structure.
Self-Aware Personalized Federated Learning
In the context of personalized federated learning (FL), the critical challenge is to balance local model improvement and global model tuning when the personal and global objectives may not be exactly aligned.
Federated Learning Challenges and Opportunities: An Outlook
Federated learning (FL) has been developed as a promising framework to leverage the resources of edge devices, enhance customers' privacy, comply with regulations, and reduce development costs.
On The Energy Statistics of Feature Maps in Pruning of Neural Networks with Skip-Connections
We propose a new structured pruning framework for compressing Deep Neural Networks (DNNs) with skip connections, based on measuring the statistical dependency of hidden layers and predicted outputs.
SPIDER: Searching Personalized Neural Architecture for Federated Learning
However, given that clients' data are invisible to the server and data distributions are non-identical across clients, a predefined architecture discovered in a centralized setting may not be an optimal solution for all the clients in FL.
Characteristic Neural Ordinary Differential Equations
While NODEs model the evolution of a latent variables as the solution to an ODE, C-NODE models the evolution of the latent variables as the solution of a family of first-order quasi-linear partial differential equations (PDEs) along curves on which the PDEs reduce to ODEs, referred to as characteristic curves.
Decentralized Multi-Target Cross-Domain Recommendation for Multi-Organization Collaborations
Recommender Systems (RSs) are operated locally by different organizations in many realistic scenarios.
FedNAS: Federated Deep Learning via Neural Architecture Search
Federated Learning (FL) is an effective learning framework used when data cannotbe centralized due to privacy, communication costs, and regulatory restrictions. While there have been many algorithmic advances in FL, significantly less effort hasbeen made on model development, and most works in FL employ predefined modelarchitectures discovered in the centralized environment.
Provable Identifiability of ReLU Neural Networks via Lasso Regularization
In this paper, the territory of LASSO is extended to the neural network model, a fashionable and powerful nonlinear regression model.
Assisted Learning for Organizations with Limited Imbalanced Data
In this work, we develop an assisted learning framework for assisting organizations to improve their learning performance.
Targeted Cross-Validation
A standard approach is to find the globally best modeling method from a set of candidate methods.
The Rate of Convergence of Variation-Constrained Deep Neural Networks
To the best of our knowledge, the rate of convergence of neural networks shown by existing works is bounded by at most the order of $n^{-1/4}$ for a sample size of $n$.
SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Training
Most existing results on Federated Learning (FL) assume the clients have ground-truth labels.
GAL: Gradient Assisted Learning for Decentralized Multi-Organization Collaborations
However, the underlying organizations may have little interest in sharing their local data, models, and objective functions.
Learning Time Series from Scale Information
Based on that, we focus on a specific but important type of scale information, the resolution/sampling rate of time series data.
Model-Free Energy Distance for Pruning DNNs
We measure a new model-free information between the feature maps and the output of the network.
THE EFFICACY OF L1 REGULARIZATION IN NEURAL NETWORKS
A crucial problem in neural networks is to select the most appropriate number of hidden neurons and obtain tight statistical risk bounds.
On Statistical Efficiency in Learning
We propose a generalized notion of Takeuchi's information criterion and prove that the proposed method can asymptotically achieve the optimal out-sample prediction loss under reasonable assumptions.
ASCII: ASsisted Classification with Ignorance Interchange
In this paper, we propose a method named ASCII for an agent to improve its classification performance through assistance from other agents.
HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients
In this work, we propose a new federated learning framework named HeteroFL to address heterogeneous clients equipped with very different computation and communication capabilities.
The Efficacy of $L_1$ Regularization in Two-Layer Neural Networks
A crucial problem in neural networks is to select the most appropriate number of hidden neurons and obtain tight statistical risk bounds.
Information Laundering for Model Privacy
In this work, we propose information laundering, a novel framework for enhancing model privacy.
Forecasting with Multiple Seasonality
An emerging number of modern applications involve forecasting time series data that exhibit both short-time dynamics and long-time seasonality.
Subcarrier-wise Backscatter Communications over Ambient OFDM for Low Power IoT
Analytical and numerical evaluations provide a proof to see the performance of the proposed method in terms of BER, data rate, and interference.
Fisher Auto-Encoders
It has been conjectured that the Fisher divergence is more robust to model uncertainty than the conventional Kullback-Leibler (KL) divergence.
Short-Range Ambient Backscatter Communication Using Reconfigurable Intelligent Surfaces
In this paper, we propose a new AmBC model over ambient orthogonal-frequency-division-multiplexing (OFDM) subcarriers in the frequency domain in conjunction with RIS for short-range communication scenarios.
Machine Learning Enabled Preamble Collision Resolution in Distributed Massive MIMO
Preamble collision is a bottleneck that impairs the performance of random access (RA) user equipment (UE) in grant-free RA (GFRA).
Meta Clustering for Collaborative Learning
We propose a framework named meta clustering to address the challenge.
Model Linkage Selection for Cooperative Learning
The main crux is to sequentially incorporate additional learners that can enhance the prediction accuracy of an existing joint model based on user-specified parameter sharing patterns across a set of learners.
Assisted Learning: A Framework for Multi-Organization Learning
In an increasing number of AI scenarios, collaborations among different organizations or agents (e. g., human and robots, mobile units) are often essential to accomplish an organization-specific mission.
Multimodal Controller for Generative Models
In the absence of the controllers, our model reduces to non-conditional generative models.
Gradient Information for Representation and Modeling
Motivated by Fisher divergence, in this paper we present a new set of information quantities which we refer to as gradient information.
Is a Classification Procedure Good Enough? A Goodness-of-Fit Assessment Tool for Classification Learning
For testing parametric classification models, the BAGofT has a broader scope than the existing methods since it is not restricted to specific parametric models (e. g., logistic regression).
Variable Grouping Based Bayesian Additive Regression Tree
We propose a two-stage method named variable grouping based Bayesian additive regression tree (GBART) with a well-developed python package gbart available.
Deep Clustering of Compressed Variational Embeddings
Motivated by the ever-increasing demands for limited communication bandwidth and low-power consumption, we propose a new methodology, named joint Variational Autoencoders with Bernoulli mixture models (VAB), for performing clustering in the compressed data domain.
Perception-Distortion Trade-off with Restricted Boltzmann Machines
In this work, we introduce a new procedure for applying Restricted Boltzmann Machines (RBMs) to missing data inference tasks, based on linearization of the effective energy function governing the distribution of observations.
Speech Emotion Recognition with Dual-Sequence LSTM Architecture
Speech Emotion Recognition (SER) has emerged as a critical component of the next generation human-machine interfacing technologies.
Supervised Encoding for Discrete Representation Learning
Classical supervised classification tasks search for a nonlinear mapping that maps each encoded feature directly to a probability mass over the labels.
Restricted Recurrent Neural Networks
Recurrent Neural Network (RNN) and its variations such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), have become standard building blocks for learning online data of sequential nature in many research areas, including natural language processing and speech data analysis.
DRASIC: Distributed Recurrent Autoencoder for Scalable Image Compression
We propose a new architecture for distributed image compression from a group of distributed data sources.
Model Selection Techniques -- An Overview
In the era of big data, analysts usually explore various statistical models or machine learning methods for observed data in order to facilitate scientific discoveries or gain predictive power.
Learning the Number of Autoregressive Mixtures in Time Series Using the Gap Statistics
We define a new distance measure between stable AR filters and draw a reference curve that is used to measure how much adding a new AR filter improves the performance of the model, and then choose the number of AR filters that has the maximum gap with the reference curve.
Bridging AIC and BIC: a new criterion for autoregression
When the data is generated from a finite order autoregression, the Bayesian information criterion is known to be consistent, and so is the new criterion.
Data-Driven Learning of the Number of States in Multi-State Autoregressive Models
In this work, we consider the class of multi-state autoregressive processes that can be used to model non-stationary time-series of interest.
