29 October 2020 in IEEE Access
Likelihood-based generative frameworks are receiving increasing attention in the deep learning community, mostly on account of their strong probabilistic foundation. Among them, Variational Autoencoders (VAEs) are reputed for their fast and tractable sampling and relatively stable training, but if not properly tuned they may easily produce poor generative performances. The loss function of Variational Autoencoders is the sum of two components, with somehow contrasting effects: the reconstruction loss , improving the quality of the resulting images, and the Kullback-Leibler divergence , acting as a regularizer of the latent space. Correctly balancing these two components is a delicate issue, and one of the major problems of VAEs. Recent techniques address the problem by allowing the network to learn the balancing factor during training, according to a suitable loss function. In this article, we show that learning can be replaced by a simple deterministic computation, expressing the balancing factor in terms of a running average of the reconstruction error over the last minibatches. As a result, we keep a constant balance between the two components along training: as reconstruction improves, we proportionally decrease KL-divergence in order to prevent its prevalence, that would forbid further improvements of the quality of reconstructions. Our technique is simple and effective: it clarifies the learning objective for the balancing factor, and it produces faster and more accurate behaviours. On typical datasets such as Cifar10 and CelebA, our technique sensibly outperforms all previous VAE architectures with comparable parameter capacity.
11 December 2024 in IEEE Internet Computing
FunLess is a Function-as-a-Service (FaaS) platform tailored for private edge cloud systems. FunLess leverages WebAssembly as its runtime environment for performance, function isolation, and support for heterogeneous devices, crucial for extending the coverage of serverless computing to private edge cloud systems. We benchmark FunLess against three production-ready, widely adopted open-source FaaS platforms—OpenFaaS, Fission, and Knative—under different deployment scenarios, characterised by the presence/absence of constrained-resource devices (Raspberry Pi 3B+) and the (in)accessibility of container orchestration technologies—Kubernetes. Our results confirm that FunLess is a suitable solution for FaaS private edge cloud systems since it achieves performance comparable to the considered FaaS alternatives while it is the only fully-deployable alternative on constrained-resource devices.
1 November 2023 in IT Professional
Function as a service (FaaS) is a serverless cloud execution model offering cost-efficiency, scalability, and simplified development by enabling developers to focus on code and delegate server management and application scaling to the serverless platform. Early FaaS implementations provided no control to users over function placement, but raising data locality-bound scenarios motivated new implementations with user-defined constraints over function allocations, e.g., to keep functions accessing a database close to the latter, with the aim of reducing latency, enhancing security, or complying with regulations. In this article, we show how, by leveraging the Allocation Priority Policies language—used for controlling function scheduling—and state-of-the-art planning tools, it is possible to enforce security properties and data-locality constraints, thereby guiding the definition of fine-grained serverless scheduling policies.
1 December 2024 in International Journal on Software Tools for Technology Transfer
15 July 2025 in Ad Hoc Networks