Multi-Agent Reinforcement Learning for Graph Discovery in D2D-Enabled Federated Learning

Augmenting federated learning (FL) with device-to-device (D2D) communications can help improve convergence speed and reduce model bias through local information exchange. However, data privacy concerns, trust constraints between devices, and unreliable wireless channels each pose challenges in finding an effective yet resource efficient D2D graph structure. In this paper, we develop a decentralized reinforcement learning (RL) method for D2D graph discovery that promotes communication of impactful datapoints over reliable links for multiple learning paradigms, while following both data and device-specific trust constraints. An independent RL agent at each device trains a policy to predict the impact of incoming links in a decentralized manner without exposure of local data or significant communication overhead. For supervised settings, the D2D graph aims to improve device-specific label diversity without compromising system-level performance. For semi-supervised settings, we enable this by incorporating distributed label propagation. For unsupervised settings, we develop a variation-based diversity metric which estimates data diversity in terms of occupied latent space. Numerical experiments on five widely used datasets confirm that the data diversity improvements induced by our method increase convergence speed by up to 3 times while reducing energy consumption by up to 5 times. They also show that our method is resilient to stragglers and changes in the aggregation interval. Finally, we show that our method offers scalability benefits for larger system sizes without increases in relative overhead, and adaptability to various downstream FL architectures and to dynamic wireless environments.

Physics-Informed Generative Approaches for Wireless Channel Modeling

In recent years, machine learning (ML) methods have become increasingly popular in wireless communication systems for several applications. A critical bottleneck for designing ML systems for wireless communications is the availability of realistic wireless channel datasets, which are extremely resource intensive to produce. To this end, the generation of realistic wireless channels plays a key role in the subsequent design of effective ML algorithms for wireless communication systems. Generative models have been proposed to synthesize channel matrices, but outputs produced by such methods may not correspond to geometrically viable channels and do not provide any insight into the scenario of interest. In this work, we aim to address both these issues by integrating a parametric, physics-based geometric channel (PBGC) modeling framework with generative methods. To address limitations with gradient flow through the PBGC model, a linearized reformulation is presented, which ensures smooth gradient flow during generative model training, while also capturing insights about the underlying physical environment. We evaluate our model against prior baselines by comparing the generated samples in terms of the 2-Wasserstein distance and through the utility of generated data when used for downstream compression tasks.

DPZV: Resource Efficient ZO Optimization For Differentially Private VFL

Vertical Federated Learning (VFL) enables collaborative model training across feature-partitioned data, yet faces significant privacy risks and inefficiencies when scaling to large models. We propose DPZV, a memory-efficient Zeroth-Order(ZO) optimization framework that integrates differential privacy (DP) with vertical federated learning, addressing three critical challenges: (1) privacy vulnerabilities from gradient leakage, (2) high computation/communication costs of first-order methods, and (3) excessive memory footprint in conventional zeroth-order approaches. Our framework eliminates backpropagation through two-point gradient estimation, reducing client memory usage by 90\% compared to first-order counterparts while enabling asynchronous communication. By strategically injecting Gaussian noise on the server, DPZV achieves rigorous $(\epsilon, \delta)$-DP guarantees without third-party trust assumptions. Theoretical analysis establishes a convergence rate matching centralized case under non-convex objectives. Extensive experiments on image and NLP benchmarks demonstrate that DPZV outperforms all baselines in accuracy while providing strong privacy assurances ($\epsilon \leq 10$) and requiring far fewer computation resources, establishing new state-of-the-art privacy-utility tradeoffs for resource-constrained VFL deployments.

Federated Sketching LoRA: On-Device Collaborative Fine-Tuning of Large Language Models

Fine-tuning large language models (LLMs) on devices is attracting increasing interest. Recent works have fused low-rank adaptation (LoRA) techniques with federated fine-tuning to mitigate challenges associated with device model sizes and data scarcity. Still, the heterogeneity of computational resources remains a critical bottleneck: while higher-rank modules generally enhance performance, varying device capabilities constrain LoRA's feasible rank range. Existing approaches attempting to resolve this issue either lack analytical justification or impose additional computational overhead, leaving a wide gap for an efficient and theoretically-grounded solution. To address these challenges, we propose federated sketching LoRA (FSLoRA), which leverages a sketching mechanism to enable devices to selectively update submatrices of global LoRA modules maintained by the server. By adjusting the sketching ratios, which determine the ranks of the submatrices on the devices, FSLoRA flexibly adapts to device-specific communication and computational constraints. We provide a rigorous convergence analysis of FSLoRA that characterizes how the sketching ratios affect the convergence rate. Through comprehensive experiments on multiple datasets and LLM models, we demonstrate FSLoRA's superior performance compared to various baselines.

Cooperative Decentralized Backdoor Attacks on Vertical Federated Learning

Federated learning (FL) is vulnerable to backdoor attacks, where adversaries alter model behavior on target classification labels by embedding triggers into data samples. While these attacks have received considerable attention in horizontal FL, they are less understood for vertical FL (VFL), where devices hold different features of the samples, and only the server holds the labels. In this work, we propose a novel backdoor attack on VFL which (i) does not rely on gradient information from the server and (ii) considers potential collusion among multiple adversaries for sample selection and trigger embedding. Our label inference model augments variational autoencoders with metric learning, which adversaries can train locally. A consensus process over the adversary graph topology determines which datapoints to poison. We further propose methods for trigger splitting across the adversaries, with an intensity-based implantation scheme skewing the server towards the trigger. Our convergence analysis reveals the impact of backdoor perturbations on VFL indicated by a stationarity gap for the trained model, which we verify empirically as well. We conduct experiments comparing our attack with recent backdoor VFL approaches, finding that ours obtains significantly higher success rates for the same main task performance despite not using server information. Additionally, our results verify the impact of collusion on attack performance.

Using Diffusion Models as Generative Replay in Continual Federated Learning -- What will Happen?

Federated learning (FL) has become a cornerstone in decentralized learning, where, in many scenarios, the incoming data distribution will change dynamically over time, introducing continuous learning (CL) problems. This continual federated learning (CFL) task presents unique challenges, particularly regarding catastrophic forgetting and non-IID input data. Existing solutions include using a replay buffer to store historical data or leveraging generative adversarial networks. Nevertheless, motivated by recent advancements in the diffusion model for generative tasks, this paper introduces DCFL, a novel framework tailored to address the challenges of CFL in dynamic distributed learning environments. Our approach harnesses the power of the conditional diffusion model to generate synthetic historical data at each local device during communication, effectively mitigating latent shifts in dynamic data distribution inputs. We provide the convergence bound for the proposed CFL framework and demonstrate its promising performance across multiple datasets, showcasing its effectiveness in tackling the complexities of CFL tasks.

Enhanced Real-Time Threat Detection in 5G Networks: A Self-Attention RNN Autoencoder Approach for Spectral Intrusion Analysis

In the rapidly evolving landscape of 5G technology, safeguarding Radio Frequency (RF) environments against sophisticated intrusions is paramount, especially in dynamic spectrum access and management. This paper presents an enhanced experimental model that integrates a self-attention mechanism with a Recurrent Neural Network (RNN)-based autoencoder for the detection of anomalous spectral activities in 5G networks at the waveform level. Our approach, grounded in time-series analysis, processes in-phase and quadrature (I/Q) samples to identify irregularities that could indicate potential jamming attacks. The model's architecture, augmented with a self-attention layer, extends the capabilities of RNN autoencoders, enabling a more nuanced understanding of temporal dependencies and contextual relationships within the RF spectrum. Utilizing a simulated 5G Radio Access Network (RAN) test-bed constructed with srsRAN 5G and Software Defined Radios (SDRs), we generated a comprehensive stream of data that reflects real-world RF spectrum conditions and attack scenarios. The model is trained to reconstruct standard signal behavior, establishing a normative baseline against which deviations, indicative of security threats, are identified. The proposed architecture is designed to balance between detection precision and computational efficiency, so the LSTM network, enriched with self-attention, continues to optimize for minimal execution latency and power consumption. Conducted on a real-world SDR-based testbed, our results demonstrate the model's improved performance and accuracy in threat detection. Keywords: self-attention, real-time intrusion detection, RNN autoencoder, Transformer architecture, LSTM, time series anomaly detection, 5G Security, spectrum access security.

Federated Learning with Dynamic Client Arrival and Departure: Convergence and Rapid Adaptation via Initial Model Construction

While most existing federated learning (FL) approaches assume a fixed set of clients in the system, in practice, clients can dynamically leave or join the system depending on their needs or interest in the specific task. This dynamic FL setting introduces several key challenges: (1) the objective function dynamically changes depending on the current set of clients, unlike traditional FL approaches that maintain a static optimization goal; (2) the current global model may not serve as the best initial point for the next FL rounds and could potentially lead to slow adaptation, given the possibility of clients leaving or joining the system. In this paper, we consider a dynamic optimization objective in FL that seeks the optimal model tailored to the currently active set of clients. Building on our probabilistic framework that provides direct insights into how the arrival and departure of different types of clients influence the shifts in optimal points, we establish an upper bound on the optimality gap, accounting for factors such as stochastic gradient noise, local training iterations, non-IIDness of data distribution, and deviations between optimal points caused by dynamic client pattern. We also propose an adaptive initial model construction strategy that employs weighted averaging guided by gradient similarity, prioritizing models trained on clients whose data characteristics align closely with the current one, thereby enhancing adaptability to the current clients. The proposed approach is validated on various datasets and FL algorithms, demonstrating robust performance across diverse client arrival and departure patterns, underscoring its effectiveness in dynamic FL environments.

Hierarchical Federated Learning with Multi-Timescale Gradient Correction

While traditional federated learning (FL) typically focuses on a star topology where clients are directly connected to a central server, real-world distributed systems often exhibit hierarchical architectures. Hierarchical FL (HFL) has emerged as a promising solution to bridge this gap, leveraging aggregation points at multiple levels of the system. However, existing algorithms for HFL encounter challenges in dealing with multi-timescale model drift, i.e., model drift occurring across hierarchical levels of data heterogeneity. In this paper, we propose a multi-timescale gradient correction (MTGC) methodology to resolve this issue. Our key idea is to introduce distinct control variables to (i) correct the client gradient towards the group gradient, i.e., to reduce client model drift caused by local updates based on individual datasets, and (ii) correct the group gradient towards the global gradient, i.e., to reduce group model drift caused by FL over clients within the group. We analytically characterize the convergence behavior of MTGC under general non-convex settings, overcoming challenges associated with couplings between correction terms. We show that our convergence bound is immune to the extent of data heterogeneity, confirming the stability of the proposed algorithm against multi-level non-i.i.d. data. Through extensive experiments on various datasets and models, we validate the effectiveness of MTGC in diverse HFL settings. The code for this project is available at \href{https://github.com/wenzhifang/MTGC}{https://github.com/wenzhifang/MTGC}.

Multi-Agent Hybrid SAC for Joint SS-DSA in CRNs

Opportunistic spectrum access has the potential to increase the efficiency of spectrum utilization in cognitive radio networks (CRNs). In CRNs, both spectrum sensing and resource allocation (SSRA) are critical to maximizing system throughput while minimizing collisions of secondary users with the primary network. However, many works in dynamic spectrum access do not consider the impact of imperfect sensing information such as mis-detected channels, which the additional information available in joint SSRA can help remediate. In this work, we examine joint SSRA as an optimization which seeks to maximize a CRN's net communication rate subject to constraints on channel sensing, channel access, and transmit power. Given the non-trivial nature of the problem, we leverage multi-agent reinforcement learning to enable a network of secondary users to dynamically access unoccupied spectrum via only local test statistics, formulated under the energy detection paradigm of spectrum sensing. In doing so, we develop a novel multi-agent implementation of hybrid soft actor critic, MHSAC, based on the QMIX mixing scheme. Through experiments, we find that our SSRA algorithm, HySSRA, is successful in maximizing the CRN's utilization of spectrum resources while also limiting its interference with the primary network, and outperforms the current state-of-the-art by a wide margin. We also explore the impact of wireless variations such as coherence time on the efficacy of the system.