In real-world applications, Federated Learning (FL) meets two challenges: (1) scalability, especially when applied to massive IoT networks, and (2) how to be robust against an environment with heterogeneous data. Realizing the first problem, we aim to design a novel FL framework named Full-stack FL (F2L). Moreover, leveraging the advantages of hierarchical network design, we propose a new labeldriven knowledge distillation (LKD) technique at the global server to address the second problem. As opposed to current knowledge distillation techniques, LKD is capable of training a student model, which consists of good knowledge from all teachers' models. Therefore, our proposed algorithm can effectively extract the knowledge of the regions' data distribution (i.e., the regional aggregated models) to reduce the divergence between clients' models when operating under the FL system with non-independent identically distributed data. Extensive experiment results reveal that: (i) our F2L method can significantly improve the overall FL efficiency in all global distillations, and (ii) F2L rapidly achieves convergence as global distillation stages occur instead of increasing on each communication cycle. Recently, Federated Learning (FL) is known as a novel distributed learning methodology for enhancing communication efficiency and ensuring privacy in traditional centralized one McMahan et al. (2017). However, the most challenge of this method for client models is non-independent and identically distributed (non-IID) data, which leads to divergence into unknown directions. Inspired by this, various works on handling non-IID were proposed in Li et al. (2020); Acar et al. (2021); Dinh et al. (2021a); Karimireddy et al. (2020); Wang et al. (2020); Zhu et al. (2021); Nguyen et al. (2022b). However, these works mainly rely on arbitrary configurations without thoroughly understanding the models' behaviors, yielding low-efficiency results. Aiming to fulfil this gap, in this work, we propose a new hierarchical FL framework using information theory by taking a deeper observation of the model's behaviors, and this framework can be realized for various FL systems with heterogeneous data. In addition, our proposed framework can trigger the FL system to be more scalable, controllable, and accessible through hierarchical architecture.

Reinforcement learning is a promising paradigm for learning robot control, allowing complex control policies to be learned without requiring a dynamics model. However, even state of the art algorithms can be difficult to tune for optimum performance. We propose employing an ensemble of multiple reinforcement learning agents, each with a different set of hyperparameters, along with a mechanism for choosing the best performing set(s) on-line. In the literature, the ensemble technique is used to improve performance in general, but the current work specifically addresses decreasing the hyperparameter tuning effort. Furthermore, our approach targets on-line learning on a single robotic system, and does not require running multiple simulators in parallel. Although the idea is generic, the Deep Deterministic Policy Gradient was the model chosen, being a representative deep learning actor-critic method with good performance in continuous action settings but known high variance. We compare our online weighted q-ensemble approach to q-average ensemble strategies addressed in literature using alternate policy training, as well as online training, demonstrating the advantage of the new approach in eliminating hyperparameter tuning. The applicability to real-world systems was validated in common robotic benchmark environments: the bipedal robot half cheetah and the swimmer. Online Weighted Q-Ensemble presented overall lower variance and superior results when compared with q-average ensembles using randomized parameterizations.

We introduce ASPiRe (Adaptive Skill Prior for RL), a new approach that leverages prior experience to accelerate reinforcement learning. Unlike existing methods that learn a single skill prior from a large and diverse dataset, our framework learns a library of different distinction skill priors (i.e., behavior priors) from a collection of specialized datasets, and learns how to combine them to solve a new task. This formulation allows the algorithm to acquire a set of specialized skill priors that are more reusable for downstream tasks; however, it also brings up additional challenges of how to effectively combine these unstructured sets of skill priors to form a new prior for new tasks. Specifically, it requires the agent not only to identify which skill prior(s) to use but also how to combine them (either sequentially or concurrently) to form a new prior. To achieve this goal, ASPiRe includes Adaptive Weight Module (AWM) that learns to infer an adaptive weight assignment between different skill priors and uses them to guide policy learning for downstream tasks via weighted Kullback-Leibler divergences. Our experiments demonstrate that ASPiRe can significantly accelerate the learning of new downstream tasks in the presence of multiple priors and show improvement on competitive baselines.

Modelling semantic similarity plays a fundamental role in lexical semantic applications. A natural way of calculating semantic similarity is to access handcrafted semantic networks, but similarity prediction can also be anticipated in a distributional vector space. Similarity calculation continues to be a challenging task, even with the latest breakthroughs in deep neural language models. We first examined popular methodologies in measuring taxonomic similarity, including edge-counting that solely employs semantic relations in a taxonomy, as well as the complex methods that estimate concept specificity. We further extrapolated three weighting factors in modelling taxonomic similarity. To study the distinct mechanisms between taxonomic and distributional similarity measures, we ran head-to-head comparisons of each measure with human similarity judgements from the perspectives of word frequency, polysemy degree and similarity intensity. Our findings suggest that without fine-tuning the uniform distance, taxonomic similarity measures can depend on the shortest path length as a prime factor to predict semantic similarity; in contrast to distributional semantics, edge-counting is free from sense distribution bias in use and can measure word similarity both literally and metaphorically; the synergy of retrofitting neural embeddings with concept relations in similarity prediction may indicate a new trend to leverage knowledge bases on transfer learning. It appears that a large gap still exists on computing semantic similarity among different ranges of word frequency, polysemous degree and similarity intensity.

The literature for fairness-aware machine learning knows a plethora of different fairness notions. It is however wellknown, that it is impossible to satisfy all of them, as certain notions contradict each other. In this paper, we take a closer look at academic performance prediction (APP) systems and try to distil which fairness notions suit this task most. For this, we scan recent literature proposing guidelines as to which fairness notion to use and apply these guidelines onto APP. Our findings suggest equalised odds as most suitable notion for APP, based on APP's WYSIWYG worldview as well as potential long-term improvements for the population.

BERT, RoBERTa, DistilBERT, XLNet: Which one to use? #KDnuggets The Absolute Basics of MLOps This article is for people who don't know a thing about MLOps or want to refresh their memory.

Of course, that is a gross over-simplification. As more models are being deployed in production, the importance of MLOps has naturally grown. There is an increasing focus on the seamless design and functioning of ML models within the overall product. Model Development can't be done in a silo given the consequences it may have on the product and business. We need an ML lifecycle that is attuned to the realities of ML-assisted products and MLOps.

Since April, DALL-E has triggered an explosion of images generated using artificial intelligence. But the technology is spreading faster than creators can shape norms around its use.

From reminding potty-training toddlers to go to the loo to telling bedtime stories and being used as a "conversation partner", voice-activated smart devices are being used to help rear children almost from the day they are born. But the rapid rise in voice assistants, including Google Home, Amazon Alexa and Apple's Siri could, new research suggests, have a long-term impact on children's social and cognitive development, specifically their empathy, compassion and critical thinking skills. "The multiple impacts on children include inappropriate responses, impeding social development and hindering learning opportunities," said Anmol Arora, co-author of research published in the journal Archives of Disease in Childhood. A key concern is that children attribute human characteristics and behaviour to devices that are, said Arora, "essentially a list of trained words and sounds mashed together to make a sentence." The children anthropomorphise and then emulate the devices, copying their failure to alter their tone, volume, emphasis or intonation.

The Barlow Twins self-supervised learning objective requires neither negative samples or asymmetric learning updates, achieving results on a par with the current state-of-the-art within Computer Vision. As such, we present Audio Barlow Twins, a novel self-supervised audio representation learning approach, adapting Barlow Twins to the audio domain. We pre-train on the large-scale audio dataset AudioSet, and evaluate the quality of the learnt representations on 18 tasks from the HEAR 2021 Challenge, achieving results which outperform, or otherwise are on a par with, the current state-of-the-art for instance discrimination self-supervised learning approaches to audio representation learning. Code at https://github.com/jonahanton/SSL_audio.