arXiv subjects

Ranjitha Prasad

Publications and source records attributed to Ranjitha Prasad.

At least 19 recordsLinked to original sources

arXiv2026

Federated Continual Learning as a Distributed Drift-Plus-Penalty Control Problem

Federated Continual Learning (FCL) is fundamental to real-world distributed learning systems, requiring models to adapt to sequential, non-IID data across clients while mitigating catastrophic forgetting and client drift. Existing approaches formulate continual learning (CL) as a sequence of per-task optimization problems, applied locally at each client and coupled through aggregation, using heuristic mechanisms such as replay, regularization, or projection-based constraints. However, forgetting in FCL is inherently a long-term, distributed phenomenon, arising from the interaction of temporal task evolution and cross-client heterogeneity, which is not explicitly regulated. In this work, we cast FCL as a stochastic control problem and propose Federated Queue-regulated Continual Learning (FedQCL), a framework based on Lyapunov drift-plus-penalty (DPP) optimization. FedQCL introduces virtual queues to track the accumulation of forgetting across tasks and clients, enabling explicit control of the stability-plasticity trade-off. By optimizing a DPP objective, the method jointly improves current-task performance while the queue-based formulation provides an interpretable and tunable mechanism to balance adaptation and retention through a single parameter, without requiring gradient projection or additional communication overhead. Empirical evaluations on standard benchmarks, including Split-CIFAR-10, Split-CIFAR-100, and Split-TinyImageNet, demonstrate that FedQCL outperforms state-of-the-art baselines with respect to accuracy while significantly reducing forgetting under heterogeneous data distributions.

cs.LG↗

arXiv2026

Channel-Adaptive Robust Aggregation for Over-the-Air Federated Learning in Heterogeneous Networks

The growing demand for privacy-preserving, data-intensive applications such as IoT, augmented reality, and autonomous systems positions Federated Learning (FL) as a key enabler in 6G networks. Over-the-Air FL (OTA-FL) leverages the superposition property of the wireless multiple access channel for efficient aggregation via simultaneous transmissions. Existing methods rely on fixed aggregation schedules and do not jointly address noise, fading, and client heterogeneity. We propose CHARGE-FL (CHannel-Adaptive Robust agGrEgation), a framework that adaptively schedules aggregation based on channel dynamics and application readiness. By combining a tailored optimization strategy with a dual-purpose precoding mechanism, CHARGE-FL mitigates channel distortion and bias from partial updates, achieving superior accuracy, stability, and convergence under realistic wireless conditions. Empirical results under realistic wireless conditions show that CHARGE-FL significantly improves accuracy, stability, and convergence over state-of-the-art OTA-FL methods, particularly in straggler-prone and noisy scenarios.

cs.LG↗

arXiv2026

Theoretical Foundations of Continual Learning via Drift-Plus-Penalty

In many real-world settings, data streams are nonstationary and arrive sequentially, requiring learning systems to adapt continuously without retraining from scratch. Continual learning (CL) addresses this challenge by incorporating new tasks while mitigating catastrophic forgetting, where learning new information degrades performance on previously acquired knowledge. We introduce a control-theoretic perspective on CL that explicitly regulates the evolution of forgetting, framing adaptation as a controlled process subject to long-term stability constraints. We focus on replay-based CL, where a finite memory buffer stores representative samples from prior tasks. We propose COntinual Learning with Drift-Plus-Penalty (COLD), a continual learning framework based on the Drift-Plus-Penalty (DPP) principle from stochastic optimization. To facilitate analysis, we also consider an oracle variant, COLD-ORACLE, as a reference benchmark. At each task, both methods minimize the current task loss while maintaining a virtual queue that tracks deviations from long-term stability on previously learned tasks, capturing the stability-plasticity trade-off as a regulated dynamical process. We establish stability and convergence guarantees that characterize this trade-off through a tunable control parameter. Experiments on standard benchmarks demonstrate that COLD consistently outperforms a broad range of state-of-the-art CL methods while providing competitive and controllable forgetting behavior through explicit regulation of stability and plasticity.

cs.LG↗

arXiv2026

Informative Perturbation Selection for Uncertainty-Aware Post-hoc Explanations

Trust and ethical concerns due to the widespread deployment of opaque machine learning (ML) models motivating the need for reliable model explanations. Post-hoc model-agnostic explanation methods addresses this challenge by learning a surrogate model that approximates the behavior of the deployed black-box ML model in the locality of a sample of interest. In post-hoc scenarios, neither the underlying model parameters nor the training are available, and hence, this local neighborhood must be constructed by generating perturbed inputs in the neighborhood of the sample of interest, and its corresponding model predictions. We propose \emph{Expected Active Gain for Local Explanations} (\texttt{EAGLE}), a post-hoc model-agnostic explanation framework that formulates perturbation selection as an information-theoretic active learning problem. By adaptively sampling perturbations that maximize the expected information gain, \texttt{EAGLE} efficiently learns a linear surrogate explainable model while producing feature importance scores along with the uncertainty/confidence estimates. Theoretically, we establish that cumulative information gain scales as $\mathcal{O}(d \log t)$, where $d$ is the feature dimension and $t$ represents the number of samples, and that the sample complexity grows linearly with $d$ and logarithmically with the confidence parameter $1/\delta$. Empirical results on tabular and image datasets corroborate our theoretical findings and demonstrate that \texttt{EAGLE} improves explanation reproducibility across runs, achieves higher neighborhood stability, and improves perturbation sample quality as compared to state-of-the-art baselines such as Tilia, US-LIME, GLIME and BayesLIME.

cs.LG↗

arXiv2026

Nishpaksh: TEC Standard-Compliant Framework for Fairness Auditing and Certification of AI Models

The growing reliance on Artificial Intelligence (AI) models in high-stakes decision-making systems, particularly within emerging telecom and 6G applications, underscores the urgent need for transparent and standardized fairness assessment frameworks. While global toolkits such as IBM AI Fairness 360 and Microsoft Fairlearn have advanced bias detection, they often lack alignment with region-specific regulatory requirements and national priorities. To address this gap, we propose Nishpaksh, an indigenous fairness evaluation tool that operationalizes the Telecommunication Engineering Centre (TEC) Standard for the Evaluation and Rating of Artificial Intelligence Systems. Nishpaksh integrates survey-based risk quantification, contextual threshold determination, and quantitative fairness evaluation into a unified, web-based dashboard. The tool employs vectorized computation, reactive state management, and certification-ready reporting to enable reproducible, audit-grade assessments, thereby addressing a critical post-standardization implementation need. Experimental validation on the COMPAS dataset demonstrates Nishpaksh's effectiveness in identifying attribute-specific bias and generating standardized fairness scores compliant with the TEC framework. The system bridges the gap between research-oriented fairness methodologies and regulatory AI governance in India, marking a significant step toward responsible and auditable AI deployment within critical infrastructure like telecommunications.

cs.CY↗

arXiv2025

Noise Resilient Over-The-Air Federated Learning In Heterogeneous Wireless Networks

In 6G wireless networks, Artificial Intelligence (AI)-driven applications demand the adoption of Federated Learning (FL) to enable efficient and privacy-preserving model training across distributed devices. Over-The-Air Federated Learning (OTA-FL) exploits the superposition property of multiple access channels, allowing edge users in 6G networks to efficiently share spectral resources and perform low-latency global model aggregation. However, these advantages come with challenges, as traditional OTA-FL techniques suffer due to the joint effects of Additive White Gaussian Noise (AWGN) at the server, fading, and both data and system heterogeneity at the participating edge devices. In this work, we propose the novel Noise Resilient Over-the-Air Federated Learning (NoROTA-FL) framework to jointly tackle these challenges in federated wireless networks. In NoROTA-FL, the local optimization problems find controlled inexact solutions, which manifests as an additional proximal constraint at the clients. This approach provides robustness against straggler-induced partial work, heterogeneity, noise, and fading. From a theoretical perspective, we leverage the zeroth- and first-order inexactness and establish convergence guarantees for non-convex optimization problems in the presence of heterogeneous data and varying system capabilities. Experimentally, we validate NoROTA-FL on real-world datasets, including FEMNIST, CIFAR10, and CIFAR100, demonstrating its robustness in noisy and heterogeneous environments. Compared to state-of-the-art baselines such as COTAF and FedProx, NoROTA-FL achieves significantly more stable convergence and higher accuracy, particularly in the presence of stragglers.

cs.LG↗

arXiv2025

Representation Learning Preserving Ignorability and Covariate Matching for Treatment Effects

Estimating treatment effects from observational data is challenging due to two main reasons: (a) hidden confounding, and (b) covariate mismatch (control and treatment groups not having identical distributions). Long lines of works exist that address only either of these issues. To address the former, conventional techniques that require detailed knowledge in the form of causal graphs have been proposed. For the latter, covariate matching and importance weighting methods have been used. Recently, there has been progress in combining testable independencies with partial side information for tackling hidden confounding. A common framework to address both hidden confounding and selection bias is missing. We propose neural architectures that aim to learn a representation of pre-treatment covariates that is a valid adjustment and also satisfies covariate matching constraints. We combine two different neural architectures: one based on gradient matching across domains created by subsampling a suitable anchor variable that assumes causal side information, followed by the other, a covariate matching transformation. We prove that approximately invariant representations yield approximate valid adjustment sets which would enable an interval around the true causal effect. In contrast to usual sensitivity analysis, where an unknown nuisance parameter is varied, we have a testable approximation yielding a bound on the effect estimate. We also outperform various baselines with respect to ATE and PEHE errors on causal benchmarks that include IHDP, Jobs, Cattaneo, and an image-based Crowd Management dataset.

cs.LG↗

arXiv2024

On the Convergence of Continual Federated Learning Using Incrementally Aggregated Gradients

The holy grail of machine learning is to enable Continual Federated Learning (CFL) to enhance the efficiency, privacy, and scalability of AI systems while learning from streaming data. The primary challenge of a CFL system is to overcome global catastrophic forgetting, wherein the accuracy of the global model trained on new tasks declines on the old tasks. In this work, we propose Continual Federated Learning with Aggregated Gradients (C-FLAG), a novel replay-memory based federated strategy consisting of edge-based gradient updates on memory and aggregated gradients on the current data. We provide convergence analysis of the C-FLAG approach which addresses forgetting and bias while converging at a rate of $O(1/\sqrt{T})$ over $T$ communication rounds. We formulate an optimization sub-problem that minimizes catastrophic forgetting, translating CFL into an iterative algorithm with adaptive learning rates that ensure seamless learning across tasks. We empirically show that C-FLAG outperforms several state-of-the-art baselines on both task and class-incremental settings with respect to metrics such as accuracy and forgetting.

cs.LG↗

arXiv2024

On Homomorphic Encryption Based Strategies for Class Imbalance in Federated Learning

Class imbalance in training datasets can lead to bias and poor generalization in machine learning models. While pre-processing of training datasets can efficiently address both these issues in centralized learning environments, it is challenging to detect and address these issues in a distributed learning environment such as federated learning. In this paper, we propose FLICKER, a privacy preserving framework to address issues related to global class imbalance in federated learning. At the heart of our contribution lies the popular CKKS homomorphic encryption scheme, which is used by the clients to privately share their data attributes, and subsequently balance their datasets before implementing the FL scheme. Extensive experimental results show that our proposed method significantly improves the FL accuracy numbers when used along with popular datasets and relevant baselines.

cs.CR↗

arXiv2023

Federated Learning for Wireless Applications: A Prototype

Wireless embedded edge devices are ubiquitous in our daily lives, enabling them to gather immense data via onboard sensors and mobile applications. This offers an amazing opportunity to train machine learning (ML) models in the realm of wireless devices for decision-making. Training ML models in a wireless setting necessitates transmitting datasets collected at the edge to a cloud parameter server, which is infeasible due to bandwidth constraints, security, and privacy issues. To tackle these challenges, Federated Learning (FL) has emerged as a distributed optimization approach to the decentralization of the model training process. In this work, we present a novel prototype to examine FL's effectiveness over bandwidth-constrained wireless channels. Through a novel design consisting of Zigbee and NI USRP devices, we propose a configuration that allows clients to broadcast synergistically local ML model updates to a central server to obtain a generalized global model. We assess the efficacy of this prototype using metrics such as global model accuracy and time complexity under varying conditions of transmission power, data heterogeneity and local learning.

cs.IT↗

arXiv2023

Seeing is Believing: A Federated Learning Based Prototype to Detect Wireless Injection Attacks

Reactive injection attacks are a class of security threats in wireless networks wherein adversaries opportunistically inject spoofing packets in the frequency band of a client thereby forcing the base-station to deploy impersonation-detection methods. Towards circumventing such threats, we implement secret-key based physical-layer signalling methods at the clients which allow the base-stations to deploy machine learning (ML) models on their in-phase and quadrature samples at the baseband for attack detection. Using Adalm Pluto based software defined radios to implement the secret-key based signalling methods, we show that robust ML models can be designed at the base-stations. However, we also point out that, in practice, insufficient availability of training datasets at the base-stations can make these methods ineffective. Thus, we use a federated learning framework in the backhaul network, wherein a group of base-stations that need to protect their clients against reactive injection threats collaborate to refine their ML models by ensuring privacy on their datasets. Using a network of XBee devices to implement the backhaul network, experimental results on our federated learning setup shows significant enhancements in the detection accuracy, thus presenting wireless security as an excellent use-case for federated learning in 6G networks and beyond.

cs.IT↗

arXiv2023

Over-The-Air Clustered Wireless Federated Learning

Privacy and bandwidth constraints have led to the use of federated learning (FL) in wireless systems, where training a machine learning (ML) model is accomplished collaboratively without sharing raw data. While using bandwidth-constrained uplink wireless channels, over-the-air (OTA) FL is preferred since the clients can transmit parameter updates simultaneously to a server. A powerful server may not be available for parameter aggregation due to increased latency and server failures. In the absence of a powerful server, decentralised strategy is employed where clients communicate with their neighbors to obtain a consensus ML model while incurring huge communication cost. In this work, we propose the OTA semi-decentralised clustered wireless FL (CWFL) and CWFL-Prox algorithms, which is communication efficient as compared to the decentralised FL strategy, while the parameter updates converge to global minima as O(1/T) for each cluster. Using the MNIST and CIFAR10 datasets, we demonstrate the accuracy performance of CWFL is comparable to the central-server based COTAF and proximal constraint based methods, while beating single-client based ML model by vast margins in accuracy.

cs.LG↗

arXiv2023

CLIMAX: An exploration of Classifier-Based Contrastive Explanations

Explainable AI is an evolving area that deals with understanding the decision making of machine learning models so that these models are more transparent, accountable, and understandable for humans. In particular, post-hoc model-agnostic interpretable AI techniques explain the decisions of a black-box ML model for a single instance locally, without the knowledge of the intrinsic nature of the ML model. Despite their simplicity and capability in providing valuable insights, existing approaches fail to deliver consistent and reliable explanations. Moreover, in the context of black-box classifiers, existing approaches justify the predicted class, but these methods do not ensure that the explanation scores strongly differ as compared to those of another class. In this work we propose a novel post-hoc model agnostic XAI technique that provides contrastive explanations justifying the classification of a black box classifier along with a reasoning as to why another class was not predicted. Our method, which we refer to as CLIMAX which is short for Contrastive Label-aware Influence-based Model Agnostic XAI, is based on local classifiers . In order to ensure model fidelity of the explainer, we require the perturbations to be such that it leads to a class-balanced surrogate dataset. Towards this, we employ a label-aware surrogate data generation method based on random oversampling and Gaussian Mixture Model sampling. Further, we propose influence subsampling in order to retaining effective samples and hence ensure sample complexity. We show that we achieve better consistency as compared to baselines such as LIME, BayLIME, and SLIME. We also depict results on textual and image based datasets, where we generate contrastive explanations for any black-box classification model where one is able to only query the class probabilities for an instance of interest.

cs.LG↗

arXiv2022

Select Wisely and Explain: Active Learning and Probabilistic Local Post-hoc Explainability

Albeit the tremendous performance improvements in designing complex artificial intelligence (AI) systems in data-intensive domains, the black-box nature of these systems leads to the lack of trustworthiness. Post-hoc interpretability methods explain the prediction of a black-box ML model for a single instance, and such explanations are being leveraged by domain experts to diagnose the underlying biases of these models. Despite their efficacy in providing valuable insights, existing approaches fail to deliver consistent and reliable explanations. In this paper, we propose an active learning-based technique called UnRAvEL (Uncertainty driven Robust Active Learning Based Locally Faithful Explanations), which consists of a novel acquisition function that is locally faithful and uses uncertainty-driven sampling based on the posterior distribution on the probabilistic locality using Gaussian process regression(GPR). We present a theoretical analysis of UnRAvEL by treating it as a local optimizer and analyzing its regret in terms of instantaneous regrets over a global optimizer. We demonstrate the efficacy of the local samples generated by UnRAvEL by incorporating different kernels such as the Matern and linear kernels in GPR. Through a series of experiments, we show that UnRAvEL outperforms the baselines with respect to stability and local fidelity on several real-world models and datasets. We show that UnRAvEL is an efficient surrogate dataset generator by deriving importance scores on this surrogate dataset using sparse linear models. We also showcase the sample efficiency and flexibility of the developed framework on the Imagenet dataset using a pre-trained ResNet model.

cs.LG↗

arXiv2021

DAGSurv: Directed Acyclic Graph Based Survival Analysis Using Deep Neural Networks

Causal structures for observational survival data provide crucial information regarding the relationships between covariates and time-to-event. We derive motivation from the information theoretic source coding argument, and show that incorporating the knowledge of the directed acyclic graph (DAG) can be beneficial if suitable source encoders are employed. As a possible source encoder in this context, we derive a variational inference based conditional variational autoencoder for causal structured survival prediction, which we refer to as DAGSurv. We illustrate the performance of DAGSurv on low and high-dimensional synthetic datasets, and real-world datasets such as METABRIC and GBSG. We demonstrate that the proposed method outperforms other survival analysis baselines such as Cox Proportional Hazards, DeepSurv and Deephit, which are oblivious to the underlying causal relationship between data entities.

cs.LG↗

arXiv2021

Path-Aware OMP Algorithms for Provenance Recovery in Wireless Networks

Low-latency provenance embedding methods have received traction in vehicular networks for their ability to track the footprint of information flow. One such known method is based on Bloom filters wherein the nodes that forward the packets appropriately choose a certain number of hash functions to embed their signatures in a shared space in the packet. Although Bloom filter methods can achieve the required accuracy level in provenance recovery, they are known to incur higher processing delay since higher number of hash functions are needed to meet the accuracy level. Motivated by this behaviour, we identify a regime of delay-constraints within which new provenance embedding methods must be proposed as Bloom filter methods are no longer applicable. To fill this research gap, we present network-coded edge embedding (NCEE) protocols that facilitate low-latency routing of packets in vehicular network applications. First, we show that the problem of designing provenance recovery methods for the NCEE protocol is equivalent to the celebrated problem of compressed sensing, however, with additional constraints of path formation on the solution. Subsequently, we present a family of path-aware orthogonal matching pursuit algorithms that jointly incorporates the sparsity and path constraints. Through extensive simulation results, we show that our algorithms enjoy low-complexity implementation, and also improve the path recovery performance when compared to path-agnostic counterparts.

cs.IT↗

arXiv2021

MultiMBNN: Matched and Balanced Causal Inference with Neural Networks

Causal inference (CI) in observational studies has received a lot of attention in healthcare, education, ad attribution, policy evaluation, etc. Confounding is a typical hazard, where the context affects both, the treatment assignment and response. In a multiple treatment scenario, we propose the neural network based MultiMBNN, where we overcome confounding by employing generalized propensity score based matching, and learning balanced representations. We benchmark the performance on synthetic and real-world datasets using PEHE, and mean absolute percentage error over ATE as metrics. MultiMBNN outperforms the state-of-the-art algorithms for CI such as TARNet and Perfect Match (PM).

stat.ME↗

arXiv2021

Hi-CI: Deep Causal Inference in High Dimensions

We address the problem of counterfactual regression using causal inference (CI) in observational studies consisting of high dimensional covariates and high cardinality treatments. Confounding bias, which leads to inaccurate treatment effect estimation, is attributed to covariates that affect both treatments and outcome. The presence of high-dimensional co-variates exacerbates the impact of bias as it is harder to isolate and measure the impact of these confounders. In the presence of high-cardinality treatment variables, CI is rendered ill-posed due to the increase in the number of counterfactual outcomes to be predicted. We propose Hi-CI, a deep neural network (DNN) based framework for estimating causal effects in the presence of large number of covariates, and high-cardinal and continuous treatment variables. The proposed architecture comprises of a decorrelation network and an outcome prediction network. In the decorrelation network, we learn a data representation in lower dimensions as compared to the original covariates and addresses confounding bias alongside. Subsequently, in the outcome prediction network, we learn an embedding of high-cardinality and continuous treatments, jointly with the data representation. We demonstrate the efficacy of causal effect prediction of the proposed Hi-CI network using synthetic and real-world NEWS datasets.

stat.ME↗