Catálogo de publicaciones - revistas

<jats:p>Unlabelled data appear in many domains and are particularly relevant to streaming applications, where even though data is abundant, labelled data is rare. To address the learning problems associated with such data, one can ignore the unlabelled data and focus only on the labelled data (supervised learning); use the labelled data and attempt to leverage the unlabelled data (semi-supervised learning); or assume some labels will be available on request (active learning). The first approach is the simplest, yet the amount of labelled data available will limit the predictive performance. The second relies on finding and exploiting the underlying characteristics of the data distribution. The third depends on an external agent to provide the required labels in a timely fashion. This survey pays special attention to methods that leverage unlabelled data in a semi-supervised setting. We also discuss the delayed labelling issue, which impacts both fully supervised and semi-supervised methods. We propose a unified problem setting, discuss the learning guarantees and existing methods, explain the differences between related problem settings. Finally, we review the current benchmarking practices and propose adaptations to enhance them.</jats:p>

<jats:p>There is a growing consensus that solutions to complex science and engineering problems require novel methodologies that are able to integrate traditional physics-based modeling approaches with state-of-the-art machine learning (ML) techniques. This paper provides a structured overview of such techniques. Application-centric objective areas for which these approaches have been applied are summarized, and then classes of methodologies used to construct physics-guided ML models and hybrid physics-ML frameworks are described. We then provide a taxonomy of these existing techniques, which uncovers knowledge gaps and potential crossovers of methods between disciplines that can serve as ideas for future research.</jats:p>

<jats:p>Voice assistants have become prevalent on a wide range of personal devices such as smartphones and smart speakers. As companies build voice assistants with extra functionalities, attacks that trick a voice assistant into performing malicious behaviors can pose a significant threat to a user’s security, privacy, and even safety. However, the diverse attacks and stand-alone defenses in the literature often lack a systematic perspective, making it challenging for designers to properly identify, understand, and mitigate the security threats against voice assistants. To overcome this problem, this article provides a thorough survey of the attacks and countermeasures for voice assistants. We systematize a broad category of relevant but seemingly unrelated attacks by the vulnerable system components and attack methods, and categorize existing countermeasures based on the defensive strategies from a system designer’s perspective. To assist designers in planning defense based on their demands, we provide a qualitative comparison of existing countermeasures by the implementation cost, usability, and security and propose practical suggestions. We envision this work can help build more reliability into voice assistants and promote research in this fast-evolving area.</jats:p>

<jats:p>Federated learning (FL) is experiencing fast booming in recent years, which is jointly promoted by the prosperity of machine learning and Artificial Intelligence along with the emerging privacy issues. In the FL paradigm, a central server and local end devices maintain the same model by exchanging model updates instead of raw data, with which the privacy of data stored on end devices is not directly revealed. In this way, the privacy violation caused by the growing collection of sensitive data can be mitigated. However, the performance of FL with a central server is reaching a bottleneck while new threats are emerging simultaneously. There are various reasons, among which the most significant ones are centralized processing, data falsification, and lack of incentives. To accelerate the proliferation of FL, blockchain-enabled FL has attracted substantial attention from both academia and industry. A considerable number of novel solutions are devised to meet the emerging demands of diverse scenarios. Blockchain-enabled FL provides both theories and techniques to improve the performances of FL from various perspectives. In this survey, we will comprehensively summarize and evaluate existing variants of blockchain-enabled FL, identify the emerging challenges, and propose potentially promising research directions in this under-explored domain.</jats:p>

<jats:p>Deep Neural Networks (DNNs) are very popular because of their high performance in various cognitive tasks in Machine Learning (ML). Recent advancements in DNNs have brought beyond human accuracy in many tasks, but at the cost of high computational complexity. To enable efficient execution of DNN inference, more and more research works, therefore, exploit the inherent error resilience of DNNs and employ Approximate Computing (AC) principles to address the elevated energy demands of DNN accelerators. This article provides a comprehensive survey and analysis of hardware approximation techniques for DNN accelerators. First, we analyze the state of the art and by identifying approximation families, we cluster the respective works with respect to the approximation type. Next, we analyze the complexity of the performed evaluations (with respect to the dataset and DNN size) to assess the efficiency, the potential, and limitations of approximate DNN accelerators. Moreover, a broad discussion is provided, regarding error metrics that are more suitable for designing approximate units for DNN accelerators as well as accuracy recovery approaches that are tailored to DNN inference. Finally, we present how Approximate Computing for DNN accelerators can go beyond energy efficiency and address reliability and security issues, as well.</jats:p>

<jats:p>Emotion recognition technology through analyzing the EEG signal is currently an essential concept in Artificial Intelligence and holds great potential in emotional health care, human-computer interaction, multimedia content recommendation, etc. Though there have been several works devoted to reviewing EEG-based emotion recognition, the content of these reviews needs to be updated. In addition, those works are either fragmented in content or only focus on specific techniques adopted in this area but neglect the holistic perspective of the entire technical routes. Hence, in this paper, we review from the perspective of researchers who try to take the first step on this topic. We review the recent representative works in the EEG-based emotion recognition research and provide a tutorial to guide the researchers to start from the beginning. The scientific basis of EEG-based emotion recognition in the psychological and physiological levels is introduced. Further, we categorize these reviewed works into different technical routes and illustrate the theoretical basis and the research motivation, which will help the readers better understand why those techniques are studied and employed. At last, existing challenges and future investigations are also discussed in this paper, which guides the researchers to decide potential future research directions.</jats:p>

<jats:p> The goal of text-to-text generation is to make machines express like a human in many applications such as conversation, summarization, and translation. It is one of the most important yet challenging tasks in natural language processing (NLP). Various neural encoder-decoder models have been proposed to achieve the goal by learning to map input text to output text. However, the input text alone often provides limited knowledge to generate the desired output, so the performance of text generation is still far from satisfaction in many real-world scenarios. To address this issue, researchers have considered incorporating (i) internal knowledge embedded in the input text and (ii) external knowledge from outside sources such as knowledge base and knowledge graph into the text generation system. This research topic is known as <jats:italic>knowledge-enhanced text generation</jats:italic> . In this survey, we present a comprehensive review of the research on this topic over the past five years. The main content includes two parts: (i) general methods and architectures for integrating knowledge into text generation; (ii) specific techniques and applications according to different forms of knowledge data. This survey can have broad audiences, researchers and practitioners, in academia and industry. </jats:p>

<jats:p>Evolutionary dynamic multi-objective optimisation (EDMO) is a relatively young but rapidly growing area of investigation. EDMO employs evolutionary approaches to handle multi-objective optimisation problems that have time-varying changes in objective functions, constraints and/or environmental parameters. Due to the simultaneous presence of dynamics and multi-objectivity in problems, the optimisation difficulty for EDMO has a marked increase compared to that for single-objective or stationary optimisation. After nearly two decades of community effort, EDMO has achieved significant advancements on various topics, including theoretic research and applications. This paper presents a broad survey and taxonomy of existing research on EDMO. Multiple research opportunities are highlighted to further promote the development of the EDMO research field.</jats:p>

<jats:p>Social media embeddedness relationships consist of online social networks formed by self-organized individual actors and significantly affect many aspects of our lives. Since the high cost and inefficiency of using population networks generated by social media embeddedness relationships to study practical issues, sampling techniques have become increasingly important than ever. Our work consists of three parts. We first comprehensively analyze current sampling selection methods, evaluation indexes, and evaluation methods in terms of technological evolution. In the second part, we systematically conduct sampling tests using representative large-scale social media datasets. The test results indicate that unequal-probability sampling methods can construct similar sample networks at the macroscale and microscale and outperform the equal-probability methods. However, non-negligible sampling errors at the mesoscale seriously affect the sampling reliability and validity. MANOVA tests show that the direct cause of sampling errors is the low in-degree nodes with medium-high betweenness located between the core and periphery, and current sampling methods can't accurately sample such complex interconnected structures. In the third part, we summarize the pros and cons of current sampling methods and provide suggestions for future work.</jats:p>

<jats:p>Recently, recommender systems have played an increasingly important role in a wide variety of commercial applications to help users find favourite products. Research in the recommender system field has traditionally focused on the accuracy of predictions and the relevance of recommendations. However, other recommendation quality measures may have a significant impact on the overall performance of a recommender system and the satisfaction of users. Hence, researchers’ attention in this field has recently shifted to include other recommender system objectives. This article aims to provide a comprehensive review of recent research efforts on recommender systems based on the objectives achieved: relevance, diversity, novelty, coverage, and serendipity. In addition, the definitions and measures associated with these objectives are reviewed. Furthermore, the article surveys the evaluation methodology used to measure the impact of the main challenges on performance and the new applications of the recommender system. Finally, new perspectives, open issues, and future directions are provided to develop the field.</jats:p>