The novel coronavirus (COVID-19) was declared as a global pandemic by the World Health Organization (WHO) after it was first discovered in Wuhan, China [1]. Over one year, the virus has infected more than 68 million people worldwide [2]. The virus can be fatal for elderly people or ones with chronic diseases [3]. Different countries across the globe have imposed several social practices and strategies to reduce the spread of the infection and to ensure the well-being of the residents. These practices and strategies include but are not limited to social distancing, restricted and authorized travels, remote work and education, reduced working staff in organizations, and frequent COVID-19 tests. These measures have been proved potential in reducing the disease spread and death in the previous pandemics [3], [4]. Several studies have focused on machine learning time series models to forecast the number of COVID-19 infections in different countries [5, 6, 7, 8, 9, 10, 11, 12, 13, 14]. This is to aid the government in designing and regulating efficient virus spread-mitigating strategies and to enable healthcare organizations for effective planning of health personnel and facilities resources. Based on the forecasted infections, the government can either make the confinement laws stricter or can ease them.

Due to the veracity and heterogeneity in network traffic, detecting anomalous events is challenging. The computational load on global servers is a significant challenge in terms of efficiency, accuracy, and scalability. Our primary motivation is to introduce a robust and scalable framework that enables efficient network anomaly detection. We address the issue of scalability and efficiency for network anomaly detection by leveraging federated learning, in which multiple participants train a global model jointly. Unlike centralized training architectures, federated learning does not require participants to upload their training data to the server, preventing attackers from exploiting the training data. Moreover, most prior works have focused on traditional centralized machine learning, making federated machine learning under-explored in network anomaly detection. Therefore, we propose a deep neural network framework that could work on low to mid-end devices detecting network anomalies while checking if a request from a specific IP address is malicious or not. Compared to multiple traditional centralized machine learning models, the deep neural federated model reduces training time overhead. The proposed method performs better than baseline machine learning techniques on the UNSW-NB15 data set as measured by experiments conducted with an accuracy of 97.21% and a faster computation time.

Despite the success of deep neural network (DNN) on sequential data (i.e., scene text and speech) recognition, it suffers from the over-confidence problem mainly due to overfitting in training with the cross-entropy loss, which may make the decision-making less reliable. Confidence calibration has been recently proposed as one effective solution to this problem. Nevertheless, the majority of existing confidence calibration methods aims at non-sequential data, which is limited if directly applied to sequential data since the intrinsic contextual dependency in sequences or the class-specific statistical prior is seldom exploited. To the end, we propose a Context-Aware Selective Label Smoothing (CASLS) method for calibrating sequential data. The proposed CASLS fully leverages the contextual dependency in sequences to construct confusion matrices of contextual prediction statistics over different classes. Class-specific error rates are then used to adjust the weights of smoothing strength in order to achieve adaptive calibration. Experimental results on sequence recognition tasks, including scene text recognition and speech recognition, demonstrate that our method can achieve the state-of-the-art performance.

Data-driven machine learning (ML) is promoted as one potential technology to be used in next-generations wireless systems. This led to a large body of research work that applies ML techniques to solve problems in different layers of the wireless transmission link. However, most of these applications rely on supervised learning which assumes that the source (training) and target (test) data are independent and identically distributed (i.i.d). This assumption is often violated in the real world due to domain or distribution shifts between the source and the target data. Thus, it is important to ensure that these algorithms generalize to out-of-distribution (OOD) data. In this context, domain generalization (DG) tackles the OOD-related issues by learning models on different and distinct source domains/datasets with generalization capabilities to unseen new domains without additional finetuning. Motivated by the importance of DG requirements for wireless applications, we present a comprehensive overview of the recent developments in DG and the different sources of domain shift. We also summarize the existing DG methods and review their applications in selected wireless communication problems, and conclude with insights and open questions.

The field of natural language processing (NLP) has made significant strides in recent years, particularly in the development of large-scale vision-language models (VLMs). These models aim to bridge the gap between text and visual information, enabling a more comprehensive understanding of multimedia data. However, as these models become larger and more complex, they also become more challenging to train and deploy. One approach to addressing this challenge is the use of sparsely-gated mixture-of-experts (MoE) techniques, which divide the model into smaller, specialized sub-models that can jointly solve a task. In this paper, we explore the effectiveness of MoE in scaling vision-language models, demonstrating its potential to achieve state-of-the-art performance on a range of benchmarks over dense models of equivalent computational cost. Our research offers valuable insights into stabilizing the training of MoE models, understanding the impact of MoE on model interpretability, and balancing the trade-offs between compute performance when scaling VLMs. We hope our work will inspire further research into the use of MoE for scaling large-scale vision-language models and other multimodal machine learning applications.

However, as reported by previous work (Zohar & Wolf, 2018; Chen et al., 2019), employing a reinforcement learning In the task of automatic program synthesis, one approach, as opposed to training using a maximum likelihood obtains pairs of matching inputs and outputs and loss to generate the single program that is available generates a computer program, in a particular as the ground truth, either hurts performance or leads to a domain-specific language (DSL), which given small increase in performance. This is despite training the each sample input returns the matching output. A MLE approach in a teacher-forcing way, in which, during key element is being able to perform an efficient training and unlike during test time, the partial programs search in the space of valid programs. Here, we considered are the prefix of the ground truth programs.

Distributed Stein Variational Gradient Descent (DSVGD) is a non-parametric distributed learning framework for federated Bayesian learning, where multiple clients jointly train a machine learning model by communicating a number of non-random and interacting particles with the server. Since communication resources are limited, selecting the clients with most informative local learning updates can improve the model convergence and communication efficiency. In this paper, we propose two selection schemes for DSVGD based on Kernelized Stein Discrepancy (KSD) and Hilbert Inner Product (HIP). We derive the upper bound on the decrease of the global free energy per iteration for both schemes, which is then minimized to speed up the model convergence. We evaluate and compare our schemes with conventional schemes in terms of model accuracy, convergence speed, and stability using various learning tasks and datasets.

In this paper, we introduce a novel self-supervised learning (SSL) loss for image representation learning. There is a growing belief that generalization in deep neural networks is linked to their ability to discriminate object shapes. Since object shape is related to the location of its parts, we propose to detect those that have been artificially misplaced. We represent object parts with image tokens and train a ViT to detect which token has been combined with an incorrect positional embedding. We then introduce sparsity in the inputs to make the model more robust to occlusions and to speed up the training. We call our method DILEMMA, which stands for Detection of Incorrect Location EMbeddings with MAsked inputs. We apply DILEMMA to MoCoV3, DINO and SimCLR and show an improvement in their performance of respectively 4.41%, 3.97%, and 0.5% under the same training time and with a linear probing transfer on ImageNet-1K. We also show full fine-tuning improvements of MAE combined with our method on ImageNet-100. We evaluate our method via fine-tuning on common SSL benchmarks. Moreover, we show that when downstream tasks are strongly reliant on shape (such as in the YOGA-82 pose dataset), our pre-trained features yield a significant gain over prior work.

We introduce a new notion of complexity of functions and we show that it has the following properties: (i) it governs a PAC Bayes-like generalization bound, (ii) for neural networks it relates to natural notions of complexity of functions (such as the variation), and (iii) it explains the generalization gap between neural networks and linear schemes. While there is a large set of papers which describes bounds that have each such property in isolation, and even some that have two, as far as we know, this is a first notion that satisfies all three of them. Moreover, in contrast to previous works, our notion naturally generalizes to neural networks with several layers. Even though the computation of our complexity is nontrivial in general, an upper-bound is often easy to derive, even for higher number of layers and functions with structure, such as period functions. An upper-bound we derive allows to show a separation in the number of samples needed for good generalization between 2 and 4-layer neural networks for periodic functions.

Entity Linking (EL) is the task of detecting mentions of entities in text and disambiguating them to a reference knowledge base. Most prevalent EL approaches assume that the reference knowledge base is complete. In practice, however, it is necessary to deal with the case of linking to an entity that is not contained in the knowledge base (NIL entity). Recent works have shown that, instead of focusing only on affinities between mentions and entities, considering inter-mention affinities can be used to represent NIL entities by producing clusters of mentions. At the same time, inter-mention affinities can help to substantially improve linking performance for known entities. With NASTyLinker, we introduce an EL approach that is aware of NIL entities and produces corresponding mention clusters while maintaining high linking performance for known entities. The approach clusters mentions and entities based on dense representations from Transformers and resolves conflicts (if more than one entity is assigned to a cluster) by computing transitive mention-entity affinities. We show the effectiveness and scalability of NASTyLinker on NILK, a dataset that is explicitly constructed to evaluate EL with respect to NIL entities. Further, we apply the presented approach to an actual EL task, namely to knowledge graph population by linking entities in Wikipedia listings, and provide an analysis of the outcome.