The metaverse, envisioned as the next digital frontier for avatar-based virtual interaction, involves high-performance models. In this dynamic environment, users' tasks frequently shift, requiring fast model personalization despite limited data. This evolution consumes extensive resources and requires vast data volumes. To address this, meta-learning emerges as an invaluable tool for metaverse users, with federated meta-learning (FML), offering even more tailored solutions owing to its adaptive capabilities. However, the metaverse is characterized by users heterogeneity with diverse data structures, varied tasks, and uneven sample sizes, potentially undermining global training outcomes due to statistical difference. Given this, an urgent need arises for smart coalition formation that accounts for these disparities. This paper introduces a dual game-theoretic framework for metaverse services involving meta-learners as workers to manage FML. A blockchain-based cooperative coalition formation game is crafted, grounded on a reputation metric, user similarity, and incentives. We also introduce a novel reputation system based on users' historical contributions and potential contributions to present tasks, leveraging correlations between past and new tasks. Finally, a Stackelberg game-based incentive mechanism is presented to attract reliable workers to participate in meta-learning, minimizing users' energy costs, increasing payoffs, boosting FML efficacy, and improving metaverse utility. Results show that our dual game framework outperforms best-effort, random, and non-uniform clustering schemes - improving training performance by up to 10%, cutting completion times by as much as 30%, enhancing metaverse utility by more than 25%, and offering up to 5% boost in training efficiency over non-blockchain systems, effectively countering misbehaving users.

Combining multiple modalities carrying complementary information through multimodal learning (MML) has shown considerable benefits for diagnosing multiple pathologies. However, the robustness of multimodal models to missing modalities is often overlooked. Most works assume modality completeness in the input data, while in clinical practice, it is common to have incomplete modalities. Existing solutions that address this issue rely on modality imputation strategies before using supervised learning models. These strategies, however, are complex, computationally costly and can strongly impact subsequent prediction models. Hence, they should be used with parsimony in sensitive applications such as healthcare. We propose HyperMM, an end-to-end framework designed for learning with varying-sized inputs. Specifically, we focus on the task of supervised MML with missing imaging modalities without using imputation before training. We introduce a novel strategy for training a universal feature extractor using a conditional hypernetwork, and propose a permutation-invariant neural network that can handle inputs of varying dimensions to process the extracted features, in a two-phase task-agnostic framework. We experimentally demonstrate the advantages of our method in two tasks: Alzheimer's disease detection and breast cancer classification. We demonstrate that our strategy is robust to high rates of missing data and that its flexibility allows it to handle varying-sized datasets beyond the scenario of missing modalities.

Recommender systems guide users through vast amounts of information by suggesting items based on their predicted preferences. Collaborative filtering-based deep learning techniques have regained popularity due to their simplicity, using only user-item interactions. Typically, these systems consist of three main components: an interaction module, a loss function, and a negative sampling strategy. Initially, researchers focused on enhancing performance by developing complex interaction modules with techniques like multi-layer perceptrons, transformers, or graph neural networks. However, there has been a recent shift toward refining loss functions and negative sampling strategies. This shift has increased interest in contrastive learning, which pulls similar pairs closer while pushing dissimilar ones apart. Contrastive learning involves key practices such as heavy data augmentation, large batch sizes, and hard-negative sampling, but these also bring challenges like high memory demands and under-utilization of some negative samples. The proposed Multi-Margin Loss (MML) addresses these challenges by introducing multiple margins and varying weights for negative samples. MML efficiently utilizes not only the hardest negatives but also other non-trivial negatives, offering a simpler yet effective loss function that outperforms more complex methods, especially when resources are limited. Experiments on two well-known datasets showed MML achieved up to a 20\% performance improvement compared to a baseline contrastive loss function with fewer negative samples.

With the wide deployment of multimodal learning systems (MMLS) in real-world scenarios, safety concerns have become increasingly prominent. The absence of systematic research into their safety is a significant barrier to progress in this field. To bridge the gap, we present the first taxonomy for MMLS safety, identifying four essential pillars of these concerns. Leveraging this taxonomy, we conduct in-depth reviews for each pillar, highlighting key limitations based on the current state of development. Finally, we pinpoint unique challenges in MMLS safety and provide potential directions for future research.

Solving the convergence issues of Generative Adversarial Networks (GANs) is one of the most outstanding problems in generative models. In this work, we propose a novel activation function to be used as output of the generator agent. This activation function is based on the Smirnov probabilistic transformation and it is specifically designed to improve the quality of the generated data. In sharp contrast with previous works, our activation function provides a more general approach that deals not only with the replication of categorical variables but with any type of data distribution (continuous or discrete). Moreover, our activation function is derivable and therefore, it can be seamlessly integrated in the backpropagation computations during the GAN training processes. To validate this approach, we evaluate our proposal against two different data sets: a) an artificially rendered data set containing a mixture of discrete and continuous variables, and b) a real data set of flow-based network traffic data containing both normal connections and cryptomining attacks. To evaluate the fidelity of the generated data, we analyze both their results in terms of quality measures of statistical nature and also regarding the use of these synthetic data to feed a nested machine learning-based classifier. The experimental results evince a clear outperformance of the GAN network tuned with this new activation function with respect to both a na\"ive mean-based generator and a standard GAN. The quality of the data is so high that the generated data can fully substitute real data for training the nested classifier without a fall in the obtained accuracy. This result encourages the use of GANs to produce high-quality synthetic data that are applicable in scenarios in which data privacy must be guaranteed.

We present a novel off-policy loss function for learning a transition model in model-based reinforcement learning. Notably, our loss is derived from the off-policy policy evaluation objective with an emphasis on correcting distribution shift. Compared to previous model-based techniques, our approach allows for greater robustness under model misspecification or distribution shift induced by learning/evaluating policies that are distinct from the data-generating policy. We provide a theoretical analysis and show empirical improvements over existing model-based off-policy evaluation methods. We provide further analysis showing our loss can be used for off-policy optimization (OPO) and demonstrate its integration with more recent improvements in OPO.

Recent state-of-the-art language models utilize a two-phase training procedure comprised of (i) unsupervised pre-training on unlabeled text, and (ii) fine-tuning for a specific supervised task. More recently, many studies have been focused on trying to improve these models by enhancing the pre-training phase, either via better choice of hyperparameters or by leveraging an improved formulation. However, the pre-training phase is computationally expensive and often done on private datasets. In this work, we present a method that leverages BERT's fine-tuning phase to its fullest, by applying an extensive number of parallel classifier heads, which are enforced to be orthogonal, while adaptively eliminating the weaker heads during training. Our method allows the model to converge to an optimal number of parallel classifiers, depending on the given dataset at hand. We conduct an extensive inter- and intra-dataset evaluations, showing that our method improves the robustness of BERT, sometimes leading to a +9\% gain in accuracy. These results highlight the importance of a proper fine-tuning procedure, especially for relatively smaller-sized datasets. Our code is attached as supplementary and our models will be made completely public.

We define a new class of Bayesian point estimators, which we refer to as risk-averse estimators. We then use this definition to formulate several axioms that we claim to be natural requirements for good inference procedures, and show that for two classes of estimation problems the axioms uniquely characterise an estimator. Namely, for estimation problems with a discrete hypothesis space, we show that the axioms lead to the MAP estimate, whereas for well-behaved, purely continuous estimation problems the axioms lead to the Wallace-Freeman estimate. Interestingly, this combined use of MAP and Wallace-Freeman estimation reflects the common practice in the Minimum Message Length (MML) community, but there these two estimators are used as approximations for the information-theoretic Strict MML estimator, whereas we derive them exactly, not as approximations, and do so with no use of encoding or information theory. Keywords: Bayes estimation, risk-averse, inference, axiomatic approach, MML, Wallace-Freeman, invariance 1. Introduction One of the fundamental statistical problems is point estimation. In a Bayesian setting, this can be described as follows. Let (x,θ) X Θ be a pair of random variables with a known joint distribution that assigns positive probability / probability density to any (x,θ) X Θ.

We present an algorithm for approximating a function defined over a $d$-dimensional manifold utilizing only noisy function values at locations sampled from the manifold with noise. To produce the approximation we do not require any knowledge regarding the manifold other than its dimension $d$. The approximation scheme is based upon the Manifold Moving Least-Squares (MMLS). The proposed algorithm is resistant to noise in both the domain and function values. Furthermore, the approximant is shown to be smooth and of approximation order of $\mathcal{O}(h^{m+1})$ for non-noisy data, where $h$ is the mesh size with respect to the manifold domain, and $m$ is the degree of a local polynomial approximation utilized in our algorithm. In addition, the proposed algorithm is linear in time with respect to the ambient-space's dimension. Thus, in case of extremely large ambient space dimension, we are able to avoid the curse of dimensionality without having to perform non-linear dimension reduction, which introduces distortions to the manifold data. Using numerical experiments, we compare the presented method to state-of-the-art algorithms for regression over manifolds and show its potential.

Contributed by Jennifer L. Eberhardt, March 26, 2017 (sent for review February 14, 2017; reviewed by James Pennebaker and Tom Tyler) Police officers speak significantly less respectfully to black than to white community members in everyday traffic stops, even after controlling for officer race, infraction severity, stop location, and stop outcome. This paper presents a systematic analysis of officer body-worn camera footage, using computational linguistic techniques to automatically measure the respect level that officers display to community members. This work demonstrates that body camera footage can be used as a rich source of data rather than merely archival evidence, and paves the way for developing powerful language-based tools for studying and potentially improving police–community relations. Using footage from body-worn cameras, we analyze the respectfulness of police officer language toward white and black community members during routine traffic stops. We develop computational linguistic methods that extract levels of respect automatically from transcripts, informed by a thin-slicing study of participant ratings of officer utterances. We find that officers speak with consistently less respect toward black versus white community members, even after controlling for the race of the officer, the severity of the infraction, the location of the stop, and the outcome of the stop. Such disparities in common, everyday interactions between police and the communities they serve have important implications for procedural justice and the building of police–community trust. Over the last several years, our nation has been rocked by an onslaught of incidents captured on video involving police officers' use of force with black suspects.