Federated learning (FL) enables a set of client devices to collaboratively train a model without sharing raw data. This process, though, operates under the constrained computation and communication resources of edge devices. These constraints combined with systems heterogeneity force some participating clients to perform fewer local updates than expected by the server, thus slowing down convergence. Exhaustive tuning of hyperparameters in FL, furthermore, can be resource-intensive, without which the convergence is adversely affected. In this work, we propose GEL, the guess and learn algorithm. GEL enables constrained edge devices to perform additional learning through guessed updates on top of gradient-based steps. These guesses aregradientless, i.e., participating clients leverage themfor free. Our generic guessing algorithm (i) can be flexibly combined with several state-of-the-art algorithms includingFedProx + GeL,FedNova,FedYogiorScaleFL; and (ii) achieves significantly improved performance when the learning rates are not best tuned. We conduct extensive experiments and show that GEL can boost empirical convergence by up to 40% in resourceconstrained networks while relieving the need for exhaustive learning rate tuning.

Existing work in fairness auditing assumes that each audit is performed independently. In this paper, we consider multiple agents working together, each auditing the same platform for different tasks. Agents have two levers: their collaboration strategy, with or without coordination beforehand, and their strategy for sampling appropriate data points. We theoretically compare the interplay of these levers. Our main findings are that (i) collaboration is generally beneficial for accurate audits, (ii) basic sampling methods often prove to be effective, and (iii) counter-intuitively, extensive coordination on queries often deteriorates audits accuracy as the number of agents increases. Experiments on three large datasets confirm our theoretical results. Our findings motivate collaboration during fairness audits of platforms that use ML models for decision-making.

Federated Unlearning (FU) aims to delete specific training data from an ML model trained using Federated Learning (FL). However, existing FU methods suffer from inefficiencies due to the high costs associated with gradient recomputation and storage. This paper presents QuickDrop, an original and efficient FU approach designed to overcome these limitations. During model training, each client uses QuickDrop to generate a compact synthetic dataset, serving as a compressed representation of the gradient information utilized during training. This synthetic dataset facilitates fast gradient approximation, allowing rapid downstream unlearning at minimal storage cost. To unlearn some knowledge from the trained model, QuickDrop clients execute stochastic gradient ascent with samples from the synthetic datasets instead of the training dataset. The tiny volume of synthetic data significantly reduces computational overhead compared to conventional FU methods. Evaluations with three standard datasets and five baselines show that, with comparable accuracy guarantees, QuickDrop reduces the unlearning duration by 463× compared to retraining the model from scratch and 65 -- 218× compared to FU baselines. QuickDrop supports both class- and client-level unlearning, multiple unlearning requests, and relearning of previously erased data.

Federated Learning (FL) is an appealing approach to training machine learning models without sharing raw data. However, standard FL algorithms are iterative and thus induce a significant communication cost. One-Shot FL (OFL) trades the iterative exchange of models between clients and the server with a single round of communication, thereby saving substantially on communication costs. Not surprisingly, OFL exhibits a performance gap in terms of accuracy with respect to FL, especially under high data heterogeneity. We introduce Fens, a novel federated ensembling scheme that approaches the accuracy of FL with the communication efficiency of OFL. Learning in Fens proceeds in two phases: first, clients train models locally and send them to the server, similar to OFL; second, clients collaboratively train a lightweight prediction aggregator model using FL. We showcase the effectiveness of Fens through exhaustive experiments spanning several datasets and heterogeneity levels. In the particular case of heterogeneously distributed CIFAR-10 dataset, Fens achieves up to a $26.9$% higher accuracy over SOTA OFL, being only $3.1$% lower than FL. At the same time, Fens incurs at most $4.3\times$ more communication than OFL, whereas FL is at least $10.9\times$ more communication-intensive than Fens.

Decentralized learning (DL) systems have been gaining popularity because they avoid raw data sharing by communicating only model parameters, hence preserving data confidentiality. However, the large size of deep neural networks poses a significant challenge for decentralized training, since each node needs to exchange gigabytes of data, overloading the network. In this paper, we address this challenge with Jwins, a communication-efficient and fully decentralized learning system that shares only a subset of parameters through sparsification. Jwins uses wavelet transform to limit the information loss due to sparsification and a randomized communication cut-off that reduces communication usage without damaging the performance of trained models. We demonstrate empirically with 96 DL nodes on non-IID datasets that Jwins can achieve similar accuracies to full-sharing DL while sending up to 64% fewer bytes. Additionally, on low communication budgets, Jwins outperforms the state-of-the-art communication-efficient DL algorithm Choco-SGD by up to 4x in terms of network savings and time.

Recommenders are central in many applications today. The most effective recommendation schemes, such as those based on collaborative filtering (CF), exploit similarities between user profiles to make recommendations, but potentially expose private data. Federated learning and decentralized learning systems address this by letting the data stay on user's machines to preserve privacy: each user performs the training on local data and only the model parameters are shared. However, sharing the model parameters across the network may still yield privacy breaches. In this paper, we present Rex, the first enclave-based decentralized CF recommender. Rex exploits Trusted execution environments (TEE), such as Intel software guard extensions (SGX), that provide shielded environments within the processor to improve convergence while preserving privacy. Firstly, Rex enables raw data sharing, which ultimately speeds up convergence and reduces the network load. Secondly, Rex fully preserves privacy. We analyze the impact of raw data sharing in both deep neural network (DNN) and matrix factorization (MF) recommenders and showcase the benefits of trusted environments in a full-fledged implementation of Rex. Our experimental results demonstrate that through raw data sharing, Rex significantly decreases the training time by 18.3 x and the network load by 2 orders of magnitude over standard decentralized approaches that share only parameters, while fully protecting privacy by leveraging trustworthy hardware enclaves with very little overhead.

This paper describes a new technique for parallelizing protein clustering, an important bioinformatics computation for the analysis of protein sequences. Protein clustering identifies groups of proteins that are similar because they share long sequences of similar amino acids. Given a collection of protein sequences, clustering can significantly reduce the computational effort required to identify all similar sequences by avoiding many negative comparisons. The challenge, however, is to build a clustering that misses as few similar sequences (or elements, more generally) as possible.