Search

In recent advancements in machine learning, federated learning allows a network of distributed clients to collaboratively develop a global model without needing to share their local data. This technique aims to safeguard privacy, countering the vulnerabilities of conventional centralized learning methods. Traditional federated learning approaches often rely on a central server to coordinate model training across clients, aiming to replicate the same model uniformly across all nodes. However, these methods overlook the significance of geographical and local data variances in vast networks, potentially affecting model effectiveness and applicability. Moreover, relying on a central server might become a bottleneck in large networks, such as the ones promoted by edge computing. Our paper introduces a novel, fully-distributed federated learning strategy called proximity-based self-federated learning that enables the self-organised creation of multiple federations of clients based on their geographic proximity and data distribution without exchanging raw data. Indeed, unlike traditional algorithms, our approach encourages clients to share and adjust their models with neighbouring nodes based on geographic proximity and model accuracy. This method not only addresses the limitations posed by diverse data distributions but also enhances the model's adaptability to different regional characteristics creating specialized models for each federation. We demonstrate the efficacy of our approach through simulations on well-known datasets, showcasing its effectiveness over the conventional centralized federated learning framework.

Today's distributed and pervasive computing addresses large-scale cyber-physical ecosystems, characterised by dense and large networks of devices capable of computation, communication and interaction with the environment and people. While most research focusses on treating these systems as "composites" (i.e., heterogeneous functional complexes), recent developments in fields such as self-organising systems and swarm robotics have opened up a complementary perspective: treating systems as "collectives" (i.e., uniform, collaborative, and self-organising groups of entities). This article explores the motivations, state of the art, and implications of this "collective computing paradigm" in software engineering, discusses its peculiar challenges, and outlines a path for future research, touching on aspects such as macroprogramming, collective intelligence, self-adaptive middleware, learning, synthesis, and experimentation of collective behaviour., Comment: 12 pages, 2 figures, Accepted for presentation at the International Workshop on Software Engineering in 2030, November 2024, Puerto Galinas (Brazil)

Recent trends like the Internet of Things (IoT) suggest a vision of dense and multi-scale deployments of computing devices in nearly all kinds of environments. A prominent engineering challenge revolves around programming the collective adaptive behaviour of such computational ecosystems. This requires abstractions able to capture concepts like ensembles (dynamic groups of cooperating devices) and collective tasks (joint activities carried out by ensembles). In this work, we consider collections of devices interacting with neighbours and that execute in nearly-synchronised sense-compute-interact rounds, where the computation is given by a single program mapping sensing values and incoming messages to output and outcoming messages. To support programming whole computational collectives, we propose the abstraction of a distributed collective process, which can be used to define at once the ensemble formation logic and its collective task. We formalise the abstraction in the eXchange Calculus (XC), a core functional language based on neighbouring values (maps from neighbours to values) where state and interaction is handled through a single primitive, exchange, and provide a corresponding implementation in the FCPP language. Then, we exercise distributed collective processes using two case studies: multi-hop message propagation and distributed monitoring of spatial properties. Finally, we discuss the features of the abstraction and its suitability for different kinds of distributed computing applications., Comment: 41 pages, 17 figures

Swarm behaviour engineering is an area of research that seeks to investigate methods and techniques for coordinating computation and action within groups of simple agents to achieve complex global goals like pattern formation, collective movement, clustering, and distributed sensing. Despite recent progress in the analysis and engineering of swarms (of drones, robots, vehicles), there is still a need for general design and implementation methods and tools that can be used to define complex swarm behaviour in a principled way. To contribute to this quest, this article proposes a new field-based coordination approach, called MacroSwarm, to design and program swarm behaviour in terms of reusable and fully composable functional blocks embedding collective computation and coordination. Based on the macroprogramming paradigm of aggregate computing, MacroSwarm builds on the idea of expressing each swarm behaviour block as a pure function, mapping sensing fields into actuation goal fields, e.g., including movement vectors. In order to demonstrate the expressiveness, compositionality, and practicality of MacroSwarm as a framework for swarm programming, we perform a variety of simulations covering common patterns of flocking, pattern formation, and collective decision-making. The implications of the inherent self-stabilisation properties of field-based computations in MacroSwarm are discussed, which formally guarantee some resilience properties and guided the design of the library.

A recurrent task in coordinated systems is managing (estimating, predicting, or controlling) signals that vary in space, such as distributed sensed data or computation outcomes. Especially in large-scale settings, the problem can be addressed through decentralised and situated computing systems: nodes can locally sense, process, and act upon signals, and coordinate with neighbours to implement collective strategies. Accordingly, in this work we devise distributed coordination strategies for the estimation of a spatial phenomenon through collaborative adaptive sampling. Our design is based on the idea of dynamically partitioning space into regions that compete and grow/shrink to provide accurate aggregate sampling. Such regions hence define a sort of virtualised space that is "fluid", since its structure adapts in response to pressure forces exerted by the underlying phenomenon. We provide an adaptive sampling algorithm in the field-based coordination framework, and prove it is self-stabilising and locally optimal. Finally, we verify by simulation that the proposed algorithm effectively carries out a spatially adaptive sampling while maintaining a tuneable trade-off between accuracy and efficiency.

Emerging application scenarios, such as cyber-physical systems (CPSs), the Internet of Things (IoT), and edge computing, call for coordination approaches addressing openness, self-adaptation, heterogeneity, and deployment agnosticism. Field-based coordination is one such approach, promoting the idea of programming system coordination declaratively from a global perspective, in terms of functional manipulation and evolution in "space and time" of distributed data structures called fields. More specifically regarding time, in field-based coordination (as in many other distributed approaches to coordination) it is assumed that local activities in each device are regulated by a fair and unsynchronised fixed clock working at the platform level. In this work, we challenge this assumption, and propose an alternative approach where scheduling is programmed in a natural way (along with usual field-based coordination) in terms of causality fields, each enacting a programmable distributed notion of a computation "cause" (why and when a field computation has to be locally computed) and how it should change across time and space. Starting from low-level platform triggers, such causality fields can be organised into multiple layers, up to high-level, collectively-computed time abstractions, to be used at the application level. This reinterpretation of time in terms of articulated causality relations allows us to express what we call "time-fluid" coordination, where scheduling can be finely tuned so as to select the triggers to react to, generally allowing to adaptively balance performance (system reactivity) and cost (resource usage) of computations. We formalise the proposed scheduling framework for field-based coordination in the context of the field calculus, discuss an implementation in the aggregate computing framework, and finally evaluate the approach via simulation on several case studies.

Recent works in contexts like the Internet of Things (IoT) and large-scale Cyber-Physical Systems (CPS) propose the idea of programming distributed systems by focussing on their global behaviour across space and time. In this view, a potentially vast and heterogeneous set of devices is considered as an "aggregate" to be programmed as a whole, while abstracting away the details of individual behaviour and exchange of messages, which are expressed declaratively. One such a paradigm, known as aggregate programming, builds on computational models inspired by field-based coordination. Existing models such as the field calculus capture interaction with neighbours by a so-called "neighbouring field" (a map from neighbours to values). This requires ad-hoc mechanisms to smoothly compose with standard values, thus complicating programming and introducing clutter in aggregate programs, libraries and domain-specific languages (DSLs). To address this key issue we introduce the novel notion of "computation against a neighbour", whereby the evaluation of certain subexpressions of the aggregate program are affected by recent corresponding evaluations in neighbours. We capture this notion in the neighbours calculus (NC), a new field calculus variant which is shown to smoothly support declarative specification of interaction with neighbours, and correspondingly facilitate the embedding of field computations as internal DSLs in common general-purpose programming languages -- as exemplified by a Scala implementation, called ScaFi. This paper formalises NC, thoroughly compares it with respect to the classic field calculus, and shows its expressiveness by means of a case study in edge computing, developed in ScaFi.

Field-based coordination has been proposed as a model for coordinating collective adaptive systems, promoting a view of distributed computations as functions manipulating data structures spread over space and evolving over time, called computational fields. The field calculus is a formal foundation for field computations, providing specific constructs for evolution (time) and neighbor interaction (space), which are handled by separate operators (called rep and nbr, respectively). This approach, however, intrinsically limits the speed of information propagation that can be achieved by their combined use. In this paper, we propose a new field-based coordination operator called share, which captures the space-time nature of field computations in a single operator that declaratively achieves: (i) observation of neighbors' values; (ii) reduction to a single local value; and (iii) update and converse sharing to neighbors of a local variable. We show that for an important class of self-stabilising computations, share can replace all occurrences of rep and nbr constructs. In addition to conceptual economy, use of the share operator also allows many prior field calculus algorithms to be greatly accelerated, which we validate empirically with simulations of frequently used network propagation and collection algorithms.

Runtime verification is a computing analysis paradigm based on observing a system at runtime (to check its expected behaviour) by means of monitors generated from formal specifications. Distributed runtime verification is runtime verification in connection with distributed systems: it comprises both monitoring of distributed systems and using distributed systems for monitoring. Aggregate computing is a programming paradigm based on a reference computing machine that is the aggregate collection of devices that cooperatively carry out a computational process: the details of behaviour, position and number of devices are largely abstracted away, to be replaced with a space-filling computational environment. In this position paper we argue, by means of simple examples, that aggregate computing is particularly well suited for implementing distributed monitors. Our aim is to foster further research on how to generate aggregate computing monitors from suitable formal specifications., Comment: In Proceedings VORTEX 2018, arXiv:1908.09302

Collecting statistic from graph-based data is an increasingly studied topic in the data mining community. We argue that these statistics have great value as well in dynamic IoT contexts: they can support complex computational activities involving distributed coordination and provision of situation recognition. We show that the HyperANF algorithm for calculating the neighbourhood function of vertices of a graph naturally allows for a fully distributed and asynchronous implementation, thanks to a mapping to the field calculus, a distribution model proposed for collective adaptive systems. This mapping gives evidence that the field calculus framework is well-suited to accommodate massively parallel computations over graphs. Furthermore, it provides a new "self-stabilising" building block which can be used in aggregate computing in several contexts, there including improved leader election or network vulnerabilities detection., Comment: In Proceedings ALP4IoT 2017, arXiv:1802.00976

Collective adaptive systems are an emerging class of networked computational systems, particularly suited in application domains such as smart cities, complex sensor networks, and the Internet of Things. These systems tend to feature large scale, heterogeneity of communication model (including opportunistic peer-to-peer wireless interaction), and require inherent self-adaptiveness properties to address unforeseen changes in operating conditions. In this context, it is extremely difficult (if not seemingly intractable) to engineer reusable pieces of distributed behaviour so as to make them provably correct and smoothly composable. Building on the field calculus, a computational model (and associated toolchain) capturing the notion of aggregate network-level computation, we address this problem with an engineering methodology coupling formal theory and computer simulation. On the one hand, functional properties are addressed by identifying the largest-to-date field calculus fragment generating self-stabilising behaviour, guaranteed to eventually attain a correct and stable final state despite any transient perturbation in state or topology, and including highly reusable building blocks for information spreading, aggregation, and time evolution. On the other hand, dynamical properties are addressed by simulation, empirically evaluating the different performances that can be obtained by switching between implementations of building blocks with provably equivalent functional properties. Overall, our methodology sheds light on how to identify core building blocks of collective behaviour, and how to select implementations that improve system performance while leaving overall system function and resiliency properties unchanged., Comment: To appear on ACM Transactions on Modeling and Computer Simulation

The complexity of large-scale distributed systems, particularly when deployed in physical space, calls for new mechanisms to address composability and reusability of collective adaptive behaviour. Computational fields have been proposed as an effective abstraction to fill the gap between the macro-level of such systems (specifying a system's collective behaviour) and the micro-level (individual devices' actions of computation and interaction to implement that collective specification), thereby providing a basis to better facilitate the engineering of collective APIs and complex systems at higher levels of abstraction. This paper proposes a full formal foundation for field computations, in terms of a core (higher-order) calculus of computational fields containing a few key syntactic constructs, and equipped with typing, denotational and operational semantics. Critically, this allows formal establishment of a link between the micro- and macro-levels of collective adaptive systems, by a result of full abstraction and adequacy for the (aggregate) denotational semantics with respect to the (per-device) operational semantics., Comment: 39 pages, 12 figures

One of the difficulties in developing collective adaptive systems is the challenge of simultaneously engineering both the desired resilient behaviour of the collective and the details of its implementation on individual devices. Aggregate computing simplifies this problem by separating these aspects into different layers of abstraction by means of a unifying notion of computational field and a functional computational model. We review the state of the art in aggregate computing, discuss the various resiliency properties it supports, and develop a roadmap of foundational problems still needing to be addressed in the continued development of this emerging discipline., Comment: In Proceedings FORECAST 2016, arXiv:1607.02001

Emerging network scenarios require the development of solid large-scale situated systems. Unfortunately, the diffusion/aggregation computational processes therein often introduce a source of complexity that hampers predictability of the overall system behaviour. Computational fields have been introduced to help engineering such systems: they are spatially distributed data structures designed to adapt their shape to the topology of the underlying (mobile) network and to the events occurring in it, with notable applications to pervasive computing, sensor networks, and mobile robots. To assure behavioural correctness, namely, correspondence of micro-level specification (single device behaviour) with macro-level behaviour (resulting global spatial pattern), we investigate the issue of self-stabilisation for computational fields. We present a tiny, expressive, and type-sound calculus of computational fields, and define sufficient conditions for self-stabilisation, defined as the ability to react to changes in the environment finding a new stable state in finite time. A type-based approach is used to provide a correct checking procedure for self-stabilisation., Comment: Logical Methods in Computer Science accepted paper, 53 pages