arXiv subjects

Atakan Aral

Publications and source records attributed to Atakan Aral.

5 recordsLinked to original sources

arXiv2026

A Fault-Tolerant Spike-Time Interface for Approximate Agreement in Distributed Neuromorphic Systems

Large neuromorphic systems contain many processing tiles that may replicate a shared control parameter such as a threshold reference. If these copies diverge, identical inputs may be processed under different intended settings. We study how tiles can reduce this disagreement when communication carries only labeled spike times and up to \(f\) sender labels may be Byzantine. A raw event stream cannot supply the one-value-per-sender input required by classical approximate agreement because a faulty sender can remain silent, flood a receiver, or report different times to different receivers. We introduce the Spike-time Interface for Faults, or \SIF, which combines paced epochs, sender attribution, per-label \FirstSpike admission, bounded timing error, and a silence sentinel. For an affine one-spike code, midpoint decoding attains the exact deterministic minimax error \(\rho=\min\{1/2,\omega/L\}\), where \(\omega\) is the residual timing uncertainty and \(L\) is the usable encoding window. \SpikeTrim applies the classical mean-subsequence-reduced (MSR) rule to the sender-indexed decoded values. For \(n\ge3f+1\), it guarantees one-step robust validity, the tight noiseless contraction factor \(f/(n-2f)\) under direct updates, an explicit worst-case asymptotic disagreement bound, and finite recovery after transient agreement-state corruption. A closed-form test determines whether a validated timing budget meets a target disagreement. Simulations illustrate the fault threshold, timing dependence, flooding resistance, and recovery. A controlled spiking classifier experiment shows an association between faster control-state alignment and lower prediction disagreement under a finite maintenance budget.

cs.AR↗

arXiv2025

Clustered Federated Learning with Hierarchical Knowledge Distillation

Clustered Federated Learning (CFL) has emerged as a powerful approach for addressing data heterogeneity and ensuring privacy in large distributed IoT environments. By clustering clients and training cluster-specific models, CFL enables personalized models tailored to groups of heterogeneous clients. However, conventional CFL approaches suffer from fragmented learning for training independent global models for each cluster and fail to take advantage of collective cluster insights. This paper advocates a shift to hierarchical CFL, allowing bi-level aggregation to train cluster-specific models at the edge and a unified global model at the cloud. This shift improves training efficiency yet might introduce communication challenges. To this end, we propose CFLHKD, a novel personalization scheme for integrating hierarchical cluster knowledge into CFL. Built upon multi-teacher knowledge distillation, CFLHKD enables inter-cluster knowledge sharing while preserving cluster-specific personalization. CFLHKD adopts a bi-level aggregation to bridge the gap between local and global learning. Extensive evaluations of standard benchmark datasets demonstrate that CFLHKD outperforms representative baselines in cluster-specific and global model accuracy and achieves a performance improvement of 3.32-7.57\%.

cs.DC↗

arXiv2025

From Silicon to Spikes: System-Wide Efficiency Gains via Exact Event-Driven Training in Neuromorphic Computing

Spiking neural networks (SNNs) promise orders-of-magnitude efficiency gains by communicating with sparse, event-driven spikes rather than dense numerical activations. However, most training pipelines either rely on surrogate-gradient approximations or require dense time-step simulations, both of which conflict with the memory, bandwidth, and scheduling constraints of neuromorphic hardware and blur precise spike timing. We introduce an analytical, event-driven learning framework that computes exact gradients for synaptic weights, programmable transmission delays, and adaptive firing thresholds, three orthogonal temporal controls that jointly shape SNN accuracy and robustness. By propagating error signals only at spike events and integrating subthreshold dynamics in closed form, the method eliminates the need to store membrane-potential traces and reduces on-chip memory traffic by up to 24x in our experiments. Across multiple sequential event-stream benchmarks, the framework improves accuracy by up to 7% over a strong surrogate-gradient baseline, while sharpening spike-timing precision and enhancing resilience to injected hardware noise. These findings indicate that aligning neuron dynamics and training dynamics with event-sparse execution can simultaneously improve functional performance and resource efficiency in neuromorphic systems.

cs.NE↗

arXiv2021

Roadmap for Edge AI: A Dagstuhl Perspective

Based on the collective input of Dagstuhl Seminar (21342), this paper presents a comprehensive discussion on AI methods and capabilities in the context of edge computing, referred as Edge AI. In a nutshell, we envision Edge AI to provide adaptation for data-driven applications, enhance network and radio access, and allow the creation, optimization, and deployment of distributed AI/ML pipelines with given quality of experience, trust, security and privacy targets. The Edge AI community investigates novel ML methods for the edge computing environment, spanning multiple sub-fields of computer science, engineering and ICT. The goal is to share an envisioned roadmap that can bring together key actors and enablers to further advance the domain of Edge AI.

cs.DC↗

arXiv2021

Multi-agent Bayesian Deep Reinforcement Learning for Microgrid Energy Management under Communication Failures

Microgrids (MGs) are important players for the future transactive energy systems where a number of intelligent Internet of Things (IoT) devices interact for energy management in the smart grid. Although there have been many works on MG energy management, most studies assume a perfect communication environment, where communication failures are not considered. In this paper, we consider the MG as a multi-agent environment with IoT devices in which AI agents exchange information with their peers for collaboration. However, the collaboration information may be lost due to communication failures or packet loss. Such events may affect the operation of the whole MG. To this end, we propose a multi-agent Bayesian deep reinforcement learning (BA-DRL) method for MG energy management under communication failures. We first define a multi-agent partially observable Markov decision process (MA-POMDP) to describe agents under communication failures, in which each agent can update its beliefs on the actions of its peers. Then, we apply a double deep Q-learning (DDQN) architecture for Q-value estimation in BA-DRL, and propose a belief-based correlated equilibrium for the joint-action selection of multi-agent BA-DRL. Finally, the simulation results show that BA-DRL is robust to both power supply uncertainty and communication failure uncertainty. BA-DRL has 4.1% and 10.3% higher reward than Nash Deep Q-learning (Nash-DQN) and alternating direction method of multipliers (ADMM) respectively under 1% communication failure probability.

eess.SY↗