Claudio Battiloro

Claudio Battiloro

Auto-generated profile, based on publicly available information

Claudio Battiloro

Department of Biostatistics, Harvard University, Boston, MA, USA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 June 2022 in IEEE Transactions on Green Communications and Networking
Verified
Journal Article
Closed access
CBClaudio Battiloro
Claudio Battiloro
PLPaolo Di Lorenzo
Paolo Di Lorenzo
MMMattia Merluzzi
Mattia Merluzzi
SBSergio Barbarossa
Sergio Barbarossa
The aim of this paper is to propose a novel dynamic resource allocation strategy for energy-efficient adaptive federated learning at the wireless network edge, with latency and learning performance guarantees. We consider a set of devices collecting local data and uploading processed information to an edge server, which runs stochastic gradient-based algorithms to perform continuous learning and adaptation. Hinging on Lyapunov stochastic optimization tools, we dynamically optimize radio parameters (e.g., set of transmitting devices, transmit powers, bits, and rates) and computation resources (e.g., CPU cycles at devices and at server) in order to strike the best trade-off between power, latency, and performance of the federated learning task. The framework admits both a model-based implementation, where the learning performance metrics are available in closed-form, and a data-driven approach, which works with online estimates of the learning performance of interest. The method is then customized to the case of federated least mean squares (LMS) estimation, and federated training of deep convolutional neural networks. Numerical results illustrate the effectiveness of our strategy to perform energy-efficient, low-latency, adaptive federated learning at the wireless network edge.

25 October 2024 in IEEE Transactions on Signal and Information Processing over Networks
Verified
Journal Article
Closed access
CBClaudio Battiloro
Claudio Battiloro
LTLucia Testa
Lucia Testa
LGLorenzo Giusti
Lorenzo Giusti
Stefania SardellittiStefania Sardellitti
Stefania Sardellitti
PLPaolo Di Lorenzo
Paolo Di Lorenzo
SBSergio Barbarossa
Sergio Barbarossa
Graph machine learning methods excel at leveraging pairwise relations present in the data. However, graphs are unable to fully capture the multi-way interactions inherent in many complex systems. An effective way to incorporate them is to model the data on higher-order combinatorial topological spaces, such as Simplicial Complexes (SCs) or Cell Complexes. For this reason, we introduce Generalized Simplicial Attention Neural Networks (GSANs), novel neural network architectures designed to process data living on simplicial complexes using masked self-attentional layers. Hinging on topological signal processing principles, we devise a series of principled self-attention mechanisms able to process data associated with simplices of various order, such as nodes, edges, triangles, and beyond. These schemes learn how to combine data associated with neighbor simplices of consecutive order in a task-oriented fashion, leveraging on the simplicial Dirac operator and its Dirac decomposition. We also prove that GSAN satisfies two fundamental properties: permutation equivariance and simplicial-awareness. Finally, we illustrate how our approach compares favorably with other simplicial and graph models when applied to several (inductive and transductive) tasks such as trajectory prediction, missing data imputation, graph classification, and simplex prediction.

20 March 2024 in IEEE Transactions on Signal Processing
Verified
Journal Article
Closed access
CBClaudio Battiloro
Claudio Battiloro
ZWZhiyang Wang
Zhiyang Wang
HRHans Riess
Hans Riess
PLPaolo Di Lorenzo
Paolo Di Lorenzo
ARAlejandro Ribeiro
Alejandro Ribeiro
In this work we introduce a convolution operation over the tangent bundle of Riemann manifolds in terms of exponentials of the Connection Laplacian operator. We define tangent bundle filters and tangent bundle neural networks (TNNs) based on this convolution operation, which are novel continuous architectures operating on tangent bundle signals, i.e. vector fields over the manifolds. Tangent bundle filters admit a spectral representation that generalizes the ones of scalar manifold filters, graph filters and standard convolutional filters in continuous time. We then introduce a discretization procedure, both in the space and time domains, to make TNNs implementable, showing that their discrete counterpart is a novel principled variant of the very recently introduced sheaf neural networks. We formally prove that this discretized architecture converges to the underlying continuous TNN. Finally, we numerically evaluate the effectiveness of the proposed architecture on various learning tasks, both on synthetic and real data, comparing it against other state-of-the-art and benchmark architectures.

22 December 2020 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
CBClaudio Battiloro
Claudio Battiloro
PLPaolo Di Lorenzo
Paolo Di Lorenzo
PBPaolo Banelli
Paolo Banelli
SBSergio Barbarossa
Sergio Barbarossa
We study decentralized estimation of time-varying signals at a fusion center, when energy harvesting sensors transmit sampled data over rate-constrained links. We propose dynamic strategies to select radio parameters, sampling set, and harvested energy at each node, with the aim of estimating a time-varying signal while ensuring: i) accuracy of the recovery procedure, and ii) stability of the batteries around a prescribed operating level. The approach is based on stochastic optimization tools, which enable adaptive optimization without the need of apriori knowledge of the statistics of radio channels and energy arrivals processes. Numerical results validate the proposed approach for decentralized signal estimation under communication and energy constraints typical of Internet of Things (IoT) scenarios.

28 January 2026 in IEEE Transactions on Cognitive Communications and Networking
Verified
Journal Article
Closed access
SFSimone Fiorellino
Simone Fiorellino
CBClaudio Battiloro
Claudio Battiloro
ESEmilio Calvanese Strinati
Emilio Calvanese Strinati
PLPaolo Di Lorenzo
Paolo Di Lorenzo
In future AI-native wireless networks, the presence of mismatches between the latent spaces of independently designed and trained deep neural network (DNN) encoders may impede mutual understanding due to the emergence of semantic channel noise. This undermines the receiver’s ability to interpret transmitted representations, thereby reducing overall system performance. To address this issue, we propose the Parseval Frame Equalizer (PFE), a zero-shot, frame-based semantic channel equalizer that aligns latent spaces of heterogeneous encoders without requiring system retraining. PFE enables dynamic signal compression and expansion, mitigating semantic noise while preserving performance on downstream tasks. Building on this capability, we introduce a dynamic optimization strategy that coordinates communication, computation, and learning resources to balance energy consumption, end-to-end (E2E) latency, and task performance in multi-agent semantic communication scenarios. Extensive simulations confirm the effectiveness of our approach in maintaining semantic consistency and meeting long-term constraints on latency and accuracy under diverse and time-varying network conditions.

11 February 2026 in IEEE Transactions on Signal and Information Processing over Networks
Verified
Journal Article
Closed access
LMLorenzo Marinucci
Lorenzo Marinucci
CBClaudio Battiloro
Claudio Battiloro
PLPaolo Di Lorenzo
Paolo Di Lorenzo
This paper introduces a novel adaptive framework for processing dynamic flow signals over simplicial complexes, extending classical least-mean-squares (LMS) methods to high-order topological domains. Building on discrete Hodge theory, we present a topological LMS algorithm that efficiently processes streaming signals observed over time-varying edge subsets. We provide a detailed stochastic analysis of the algorithm, deriving its stability conditions, steady-state mean-square-error, and convergence speed, while exploring the impact of edge sampling on performance. We also propose strategies to design optimal edge sampling probabilities, minimizing rate while ensuring desired estimation accuracy. Assuming partial knowledge of the complex structure (e.g., the underlying graph), we introduce an adaptive topology inference method that integrates with the proposed LMS framework. Additionally, we propose a distributed version of the algorithm and analyze its stability and mean-square-error properties. Empirical results on synthetic and real-world traffic data demonstrate that our approach, in both centralized and distributed settings, outperforms graph-based LMS methods by leveraging higher-order topological features.