Search

Federated learning (FL) has emerged as a promising framework for distributed machine learning. It enables collaborative learning among multiple clients, utilizing distributed data and computing resources. However, FL faces challenges in balancing privacy guarantees, communication efficiency, and overall model accuracy. In this work, we introduce CorBin-FL, a privacy mechanism that uses correlated binary stochastic quantization to achieve differential privacy while maintaining overall model accuracy. The approach uses secure multi-party computation techniques to enable clients to perform correlated quantization of their local model updates without compromising individual privacy. We provide theoretical analysis showing that CorBin-FL achieves parameter-level local differential privacy (PLDP), and that it asymptotically optimizes the privacy-utility trade-off between the mean square error utility measure and the PLDP privacy measure. We further propose AugCorBin-FL, an extension that, in addition to PLDP, achieves user-level and sample-level central differential privacy guarantees. For both mechanisms, we derive bounds on privacy parameters and mean squared error performance measures. Extensive experiments on MNIST and CIFAR10 datasets demonstrate that our mechanisms outperform existing differentially private FL mechanisms, including Gaussian and Laplacian mechanisms, in terms of model accuracy under equal PLDP privacy budgets.

We study the problem of system identification for stochastic continuous-time dynamics, based on a single finite-length state trajectory. We present a method for estimating the possibly unstable open-loop matrix by employing properly randomized control inputs. Then, we establish theoretical performance guarantees showing that the estimation error decays with trajectory length, a measure of excitability, and the signal-to-noise ratio, while it grows with dimension. Numerical illustrations that showcase the rates of learning the dynamics, will be provided as well. To perform the theoretical analysis, we develop new technical tools that are of independent interest. That includes non-asymptotic stochastic bounds for highly non-stationary martingales and generalized laws of iterated logarithms, among others.

This paper presents a comprehensive review of cardiorespiratory auscultation sensing devices which is useful for understanding the theoretical aspects of sensing devices, as well as practical notes to design novel sensing devices. One of the methods to design a stethoscope is using electret condenser microphones (ECM). In this paper, we first introduce the acoustic properties of the heart and lungs, as well as a brief history of stethoscope evolution. Then, we discuss the basic concept of ECM sensors and a recent stethoscope based on this technology. In response to the limitations of ECM-based systems, we explore the potential of microelectromechanical systems (MEMS), particularly focusing on piezoelectric transducer (PZT) sensors. This paper comprehensively reviews sensing technologies, emphasizing innovative MEMS-based designs for wearable cardiopulmonary auscultation in the past decade. To our knowledge, this is the first paper to summarize ECM and MEMS applications for heart and lung sound analysis. Keywords: Micro-electro-mechanical Systems (MEMS); Electret Condenser Microphone (ECM); Wearable Sensing Devices; Cardiorespiratory Auscultation; Phonocardiography (PCG); Heart Sound; Lung Sound

Speech in-painting is the task of regenerating missing audio contents using reliable context information. Despite various recent studies in multi-modal perception of audio in-painting, there is still a need for an effective infusion of visual and auditory information in speech in-painting. In this paper, we introduce a novel sequence-to-sequence model that leverages the visual information to in-paint audio signals via an encoder-decoder architecture. The encoder plays the role of a lip-reader for facial recordings and the decoder takes both encoder outputs as well as the distorted audio spectrograms to restore the original speech. Our model outperforms an audio-only speech in-painting model and has comparable results with a recent multi-modal speech in-painter in terms of speech quality and intelligibility metrics for distortions of 300 ms to 1500 ms duration, which proves the effectiveness of the introduced multi-modality in speech in-painting.

The process of reconstructing missing parts of speech audio from context is called speech in-painting. Human perception of speech is inherently multi-modal, involving both audio and visual (AV) cues. In this paper, we introduce and study a sequence-to-sequence (seq2seq) speech in-painting model that incorporates AV features. Our approach extends AV speech in-painting techniques to scenarios where both audio and visual data may be jointly corrupted. To achieve this, we employ a multi-modal training paradigm that boosts the robustness of our model across various conditions involving acoustic and visual distortions. This makes our distortion-aware model a plausible solution for real-world challenging environments. We compare our method with existing transformer-based and recurrent neural network-based models, which attempt to reconstruct missing speech gaps ranging from a few milliseconds to over a second. Our experimental results demonstrate that our novel seq2seq architecture outperforms the state-of-the-art transformer solution by 38.8% in terms of enhancing speech quality and 7.14% in terms of improving speech intelligibility. We exploit a multi-task learning framework that simultaneously performs lip-reading (transcribing video components to text) while reconstructing missing parts of the associated speech.

Explaining deep learning models operating on time series data is crucial in various applications of interest which require interpretable and transparent insights from time series signals. In this work, we investigate this problem from an information theoretic perspective and show that most existing measures of explainability may suffer from trivial solutions and distributional shift issues. To address these issues, we introduce a simple yet practical objective function for time series explainable learning. The design of the objective function builds upon the principle of information bottleneck (IB), and modifies the IB objective function to avoid trivial solutions and distributional shift issues. We further present TimeX++, a novel explanation framework that leverages a parametric network to produce explanation-embedded instances that are both in-distributed and label-preserving. We evaluate TimeX++ on both synthetic and real-world datasets comparing its performance against leading baselines, and validate its practical efficacy through case studies in a real-world environmental application. Quantitative and qualitative evaluations show that TimeX++ outperforms baselines across all datasets, demonstrating a substantial improvement in explanation quality for time series data. The source code is available at \url{https://github.com/zichuan-liu/TimeXplusplus}., Comment: Accepted by International Conference on Machine Learning (ICML 2024)

Over the past two decades, the surge in video streaming applications has been fueled by the increasing accessibility of the internet and the growing demand for network video. As users with varying internet speeds and devices seek high-quality video, transcoding becomes essential for service providers. In this paper, we introduce a parametric rate-distortion (R-D) transcoding model. Our model excels at predicting transcoding distortion at various rates without the need for encoding the video. This model serves as a versatile tool that can be used to achieve visual quality improvement (in terms of PSNR) via trans-sizing. Moreover, we use our model to identify visually lossless and near-zero-slope bitrate ranges for an ingest video. Having this information allows us to adjust the transcoding target bitrate while introducing visually negligible quality degradations. By utilizing our model in this manner, quality improvements up to 2 dB and bitrate savings of up to 46% of the original target bitrate are possible. Experimental results demonstrate the efficacy of our model in video transcoding rate distortion prediction.

This work presents a Fourier analysis framework for the non-interactive source simulation (NISS) problem. Two distributed agents observe a pair of sequences $X^d$ and $Y^d$ drawn according to a joint distribution $P_{X^dY^d}$. The agents aim to generate outputs $U=f_d(X^d)$ and $V=g_d(Y^d)$ with a joint distribution sufficiently close in total variation to a target distribution $Q_{UV}$. Existing works have shown that the NISS problem with finite-alphabet outputs is decidable. For the binary-output NISS, an upper-bound to the input complexity was derived which is $O(\exp\operatorname{poly}(\frac{1}{\epsilon}))$. In this work, the input complexity and algorithm design are addressed in several classes of NISS scenarios. For binary-output NISS scenarios with doubly-symmetric binary inputs, it is shown that the input complexity is $\Theta(\log{\frac{1}{\epsilon}})$, thus providing a super-exponential improvement in input complexity. An explicit characterization of the simulating pair of functions is provided. For general finite-input scenarios, a constructive algorithm is introduced that explicitly finds the simulating functions $(f_d(X^d),g_d(Y^d))$. The approach relies on a novel Fourier analysis framework. Various numerical simulations of NISS scenarios with IID inputs are provided. Furthermore, to illustrate the general applicability of the Fourier framework, several examples with non-IID inputs, including entanglement-assisted NISS and NISS with Markovian inputs are provided.

Contextual bandits constitute a classical framework for decision-making under uncertainty. In this setting, the goal is to learn the arms of highest reward subject to contextual information, while the unknown reward parameters of each arm need to be learned by experimenting that specific arm. Accordingly, a fundamental problem is that of balancing exploration (i.e., pulling different arms to learn their parameters), versus exploitation (i.e., pulling the best arms to gain reward). To study this problem, the existing literature mostly considers perfectly observed contexts. However, the setting of partial context observations remains unexplored to date, despite being theoretically more general and practically more versatile. We study bandit policies for learning to select optimal arms based on the data of observations, which are noisy linear functions of the unobserved context vectors. Our theoretical analysis shows that the Thompson sampling policy successfully balances exploration and exploitation. Specifically, we establish the followings: (i) regret bounds that grow poly-logarithmically with time, (ii) square-root consistency of parameter estimation, and (iii) scaling of the regret with other quantities including dimensions and number of arms. Extensive numerical experiments with both real and synthetic data are presented as well, corroborating the efficacy of Thompson sampling. To establish the results, we introduce novel martingale techniques and concentration inequalities to address partially observed dependent random variables generated from unspecified distributions, and also leverage problem-dependent information to sharpen probabilistic bounds for time-varying suboptimality gaps. These techniques pave the road towards studying other decision-making problems with contextual information as well as partial observations., Comment: 43 pages

Graphical models capture relations between entities in a wide range of applications including social networks, biology, and natural language processing, among others. Graph neural networks (GNN) are neural models that operate over graphs, enabling the model to leverage the complex relationships and dependencies in graph-structured data. A graph explanation is a subgraph which is an `almost sufficient' statistic of the input graph with respect to its classification label. Consequently, the classification label is invariant, with high probability, to perturbations of graph edges not belonging to its explanation subgraph. This work considers two methods for leveraging such perturbation invariances in the design and training of GNNs. First, explanation-assisted learning rules are considered. It is shown that the sample complexity of explanation-assisted learning can be arbitrarily smaller than explanation-agnostic learning. Next, explanation-assisted data augmentation is considered, where the training set is enlarged by artificially producing new training samples via perturbation of the non-explanation edges in the original training set. It is shown that such data augmentation methods may improve performance if the augmented data is in-distribution, however, it may also lead to worse sample complexity compared to explanation-agnostic learning rules if the augmented data is out-of-distribution. Extensive empirical evaluations are provided to verify the theoretical analysis., Comment: 21 pages, 6 figures, 4 tables

In task-based quantization, a multivariate analog signal is transformed into a digital signal using a limited number of low-resolution analog-to-digital converters (ADCs). This process aims to minimize a fidelity criterion, which is assessed against an unobserved task variable that is correlated with the analog signal. The scenario models various applications of interest such as channel estimation, medical imaging applications, and object localization. This work explores the integration of analog processing components -- such as analog delay elements, polynomial operators, and envelope detectors -- prior to ADC quantization. Specifically, four scenarios, involving different collections of analog processing operators are considered: (i) arbitrary polynomial operators with analog delay elements, (ii) limited-degree polynomial operators, excluding delay elements, (iii) sequences of envelope detectors, and (iv) a combination of analog delay elements and linear combiners. For each scenario, the minimum achievable distortion is quantified through derivation of computable expressions in various statistical settings. It is shown that analog processing can significantly reduce the distortion in task reconstruction. Numerical simulations in a Gaussian example are provided to give further insights into the aforementioned analog processing gains.

This work considers the non-interactive source simulation problem (NISS). In the standard NISS scenario, a pair of distributed agents, Alice and Bob, observe a distributed binary memoryless source $(X^d,Y^d)$ generated based on joint distribution $P_{X,Y}$. The agents wish to produce a pair of discrete random variables $(U_d,V_d)$ with joint distribution $P_{U_d,V_d}$, such that $P_{U_d,V_d}$ converges in total variation distance to a target distribution $Q_{U,V}$. Two variations of the standard NISS scenario are considered. In the first variation, in addition to $(X^d,Y^d)$ the agents have access to a shared Bell state. The agents each measure their respective state, using a measurement of their choice, and use its classical output along with $(X^d,Y^d)$ to simulate the target distribution. This scenario is called the entanglement-assisted NISS (EA-NISS). In the second variation, the agents have access to a classical common random bit $Z$, in addition to $(X^d,Y^d)$. This scenario is called the classical common randomness NISS (CR-NISS). It is shown that for binary-output NISS scenarios, the set of feasible distributions for EA-NISS and CR-NISS are equal with each other. Hence, there is not quantum advantage in these EA-NISS scenarios. For non-binary output NISS scenarios, it is shown through an example that there are distributions that are feasible in EA-NISS but not in CR-NISS. This shows that there is a quantum advantage in non-binary output EA-NISS.

Graph Neural Networks (GNNs) have received increasing attention due to their ability to learn from graph-structured data. To open the black-box of these deep learning models, post-hoc instance-level explanation methods have been proposed to understand GNN predictions. These methods seek to discover substructures that explain the prediction behavior of a trained GNN. In this paper, we show analytically that for a large class of explanation tasks, conventional approaches, which are based on the principle of graph information bottleneck (GIB), admit trivial solutions that do not align with the notion of explainability. Instead, we argue that a modified GIB principle may be used to avoid the aforementioned trivial solutions. We further introduce a novel factorized explanation model with theoretical performance guarantees. The modified GIB is used to analyze the structural properties of the proposed factorized explainer. We conduct extensive experiments on both synthetic and real-world datasets to validate the effectiveness of our proposed factorized explainer., Comment: AAAI 24

Video streaming often requires transcoding content into different resolutions and bitrates to match the recipient's internet speed and screen capabilities. Video encoders like x264 offer various presets, each with different tradeoffs between transcoding time and rate-distortion performance. Choosing the best preset for video transcoding is difficult, especially for live streaming, as trying all the presets and choosing the best one is not feasible. One solution is to predict each preset's transcoding time and select the preset that ensures the highest quality while adhering to live streaming time constraints. Prediction of video transcoding time is also critical in minimizing streaming delays, deploying resource management algorithms, and load balancing. We propose a learning-based framework for predicting the transcoding time of videos across various presets. Our predictor's features for video transcoding time prediction are derived directly from the ingested stream, primarily from the header or metadata. As a result, only minimal additional delay is incurred for feature extraction, rendering our approach ideal for live-streaming applications. We evaluated our learning-based transcoding time prediction using a dataset of videos. The results demonstrate that our framework can accurately predict the transcoding time for different presets, with a mean absolute percentage error (MAPE) of nearly 5.0%. Leveraging these predictions, we then select the most suitable transcoding preset for live video streaming. Utilizing our transcoding time prediction-based preset selection improved Peak Signal-to-Noise Ratio (PSNR) of up to 5 dB., Comment: 16 pages, 6 figures

Randomized experiments are a powerful methodology for data-driven evaluation of decisions or interventions. Yet, their validity may be undermined by network interference. This occurs when the treatment of one unit impacts not only its outcome but also that of connected units, biasing traditional treatment effect estimations. Our study introduces a new framework to accommodate complex and unknown network interference, moving beyond specialized models in the existing literature. Our framework, termed causal message-passing, is grounded in high-dimensional approximate message passing methodology. It is tailored for multi-period experiments and is particularly effective in settings with many units and prevalent network interference. The framework models causal effects as a dynamic process where a treated unit's impact propagates through the network via neighboring units until equilibrium is reached. This approach allows us to approximate the dynamics of potential outcomes over time, enabling the extraction of valuable information before treatment effects reach equilibrium. Utilizing causal message-passing, we introduce a practical algorithm to estimate the total treatment effect, defined as the impact observed when all units are treated compared to the scenario where no unit receives treatment. We demonstrate the effectiveness of this approach across five numerical scenarios, each characterized by a distinct interference structure.

Graph Neural Networks (GNNs) are neural models that leverage the dependency structure in graphical data via message passing among the graph nodes. GNNs have emerged as pivotal architectures in analyzing graph-structured data, and their expansive application in sensitive domains requires a comprehensive understanding of their decision-making processes -- necessitating a framework for GNN explainability. An explanation function for GNNs takes a pre-trained GNN along with a graph as input, to produce a `sufficient statistic' subgraph with respect to the graph label. A main challenge in studying GNN explainability is to provide fidelity measures that evaluate the performance of these explanation functions. This paper studies this foundational challenge, spotlighting the inherent limitations of prevailing fidelity metrics, including $Fid_+$, $Fid_-$, and $Fid_\Delta$. Specifically, a formal, information-theoretic definition of explainability is introduced and it is shown that existing metrics often fail to align with this definition across various statistical scenarios. The reason is due to potential distribution shifts when subgraphs are removed in computing these fidelity measures. Subsequently, a robust class of fidelity measures are introduced, and it is shown analytically that they are resilient to distribution shift issues and are applicable in a wide range of scenarios. Extensive empirical analysis on both synthetic and real datasets are provided to illustrate that the proposed metrics are more coherent with gold standard metrics. The source code is available at https://trustai4s-lab.github.io/fidelity., Comment: Accepted by International Conference on Learning Representations (ICLR 2024); 26 Pages, 12 figures

Image retargeting aims to alter the size of the image with attention to the contents. One of the main obstacles to training deep learning models for image retargeting is the need for a vast labeled dataset. Labeled datasets are unavailable for training deep learning models in the image retargeting tasks. As a result, we present a new supervised approach for training deep learning models. We use the original images as ground truth and create inputs for the model by resizing and cropping the original images. A second challenge is generating different image sizes in inference time. However, regular convolutional neural networks cannot generate images of different sizes than the input image. To address this issue, we introduced a new method for supervised learning. In our approach, a mask is generated to show the desired size and location of the object. Then the mask and the input image are fed to the network. Comparing image retargeting methods and our proposed method demonstrates the model's ability to produce high-quality retargeted images. Afterward, we compute the image quality assessment score for each output image based on different techniques and illustrate the effectiveness of our approach., Comment: 18 pages, 5 figures

Dataset obfuscation refers to techniques in which random noise is added to the entries of a given dataset, prior to its public release, to protect against leakage of private information. In this work, dataset obfuscation under two objectives is considered: i) rank-preservation: to preserve the row ordering in the obfuscated dataset induced by a given rank function, and ii) anonymity: to protect user anonymity under fingerprinting attacks. The first objective, rank-preservation, is of interest in applications such as the design of search engines and recommendation systems, feature matching, and social network analysis. Fingerprinting attacks, considered in evaluating the anonymity objective, are privacy attacks where an attacker constructs a fingerprint of a victim based on its observed activities, such as online web activities, and compares this fingerprint with information extracted from a publicly released obfuscated dataset to identify the victim. By evaluating the performance limits of a class of obfuscation mechanisms over asymptotically large datasets, a fundamental trade-off is quantified between rank-preservation and user anonymity. Single-letter obfuscation mechanisms are considered, where each entry in the dataset is perturbed by independent noise, and their fundamental performance limits are characterized by leveraging large deviation techniques. The optimal obfuscating test-channel, optimizing the privacy-utility tradeoff, is characterized in the form of a convex optimization problem which can be solved efficiently. Numerical simulations of various scenarios are provided to verify the theoretical derivations.

Auscultation provides a rich diversity of information to diagnose cardiovascular and respiratory diseases. However, sound auscultation is challenging due to noise. In this study, a modified version of the affine non-negative matrix factorization (NMF) approach is proposed to blindly separate lung and heart sounds recorded by a digital stethoscope. This method applies a novel NMF algorithm, which embodies a parallel structure of multilayer units on the input signal, to find a proper estimation of source signals. Another key innovation is the use of the periodic property of the signals which improves accuracy compared to previous works. The method is tested on 100 cases. Each case consists of two synthesized mixtures of real measurements. The effect of different parameters is discussed, and the results are compared to other current methods. Results demonstrate improvements in the source-to-distortion ratio (SDR), source-to-interference ratio (SIR), and source-to-artifacts ratio (SAR) of heart and lung sounds, respectively.

Endoscopy is a valuable tool for the early diagnosis of colon cancer. However, it requires the expertise of endoscopists and is a time-consuming process. In this work, we propose a new multi-label classification method, which considers two aspects of learning approaches (local and global views) for endoscopic image classification. The model consists of a Swin transformer branch and a modified VGG16 model as a CNN branch. To help the learning process of the CNN branch, the model employs saliency maps and endoscopy images and concatenates them. The results demonstrate that this method performed well for endoscopic medical images by utilizing local and global features of the images. Furthermore, quantitative evaluations prove the proposed method's superiority over state-of-the-art works., Comment: 5 pages, 3 figures