ACM Computing Surveys最新文献

This survey paper proposes a clearer view of natural language reasoning in the field of Natural Language Processing (NLP), both conceptually and practically. Conceptually, we provide a distinct definition for natural language reasoning in NLP, based on both philosophy and NLP scenarios, discuss what types of tasks require reasoning, and introduce a taxonomy of reasoning. Practically, we conduct a comprehensive literature review on natural language reasoning in NLP, mainly covering classical logical reasoning, natural language inference, multi-hop question answering, and commonsense reasoning. The paper also identifies and views backward reasoning, a powerful paradigm for multi-step reasoning, and introduces defeasible reasoning as one of the most important future directions in natural language reasoning research. We focus on single-modality unstructured natural language text, excluding neuro-symbolic research and mathematical reasoning.

Deep-learning (DL) performs well in computer-vision and medical-imaging automated decision-making applications. A bottleneck of DL stems from the large amount of labelled data required to train accurate models that generalise well. Data scarcity and imbalance are common problems in imaging applications that can lead DL models towards biased decision making. A solution to this problem is synthetic data. Synthetic data is an inexpensive substitute to real data for improved accuracy and generalisability of DL models. This survey reviews the recent methods published in relation to the creation and use of synthetic data for computer-vision and medical-imaging DL applications. The focus will be on applications that utilised synthetic data to improve DL models by either incorporating an increased diversity of data that is difficult to obtain in real life, or by reducing a bias caused by class imbalance. Computer-graphics software and generative networks are the most popular data generation techniques encountered in the literature. We highlight their suitability for typical computer-vision and medical-imaging applications, and present promising avenues for research to overcome their computational and theoretical limitations.

One hurdle to accurate indoor localization using time-based networks is the presence of Non-Line-Of-Sight (NLOS) and multipath signals, affecting the accuracy of ranging in indoor environments. NLOS identification and mitigation have been studied over the years and applied to different time-based networks, with most works considering NLOS links with WiFi and UWB channels. In this paper, we discuss the effects and challenges of NLOS conditions on indoor localization and present current state-of-the-art approaches to NLOS identification and mitigation in literature. We survey these approaches and classify them under different categories together with their merits and demerits. We further categorize approaches to tackle NLOS effects into single and hybrid measurement-based approaches in this work. Lessons learnt from the survey with future directions are also presented in this paper.

Rapid progress in the CMOS technology for the past 25 years has increased the vulnerability of processors towards faults. Subsequently, focus of computer architects shifted towards designing fault-tolerance methods for processor architectures. Concurrently, chip designers encountered high order challenges for designing fault tolerant processor architectures. For processor cores, redundancy-based fault tolerance methods for fault detection at core level, micro-architectural level ,thread level , and software level are discussed. Similar applicable redundancy-based fault tolerance methods for cache memory, and hardware accelerators are presented in the article. Recent trends in fault tolerant quantum computing and quantum error correction are also discussed. The classification of state-of-the-art techniques is presented in the survey would help the researchers to organize their work on established lines.

Despite its astounding success in learning deeper multi-dimensional data, the performance of deep learning declines on new unseen tasks mainly due to its focus on same-distribution prediction. Moreover, deep learning is notorious for poor generalization from few samples. Meta-learning is a promising approach that addresses these issues by adapting to new tasks with few-shot datasets. This survey first briefly introduces meta-learning and then investigates state-of-the-art meta-learning methods and recent advances in: (i) metric-based, (ii) memory-based, (iii), and learning-based methods. Finally, current challenges and insights for future researches are discussed.

Background: Accurate effort estimation is crucial for planning in Agile iterative development. Agile estimation generally relies on consensus-based methods like planning poker, which require less time and information than other formal methods (e.g., COSMIC) but are prone to inaccuracies. Understanding the common reasons for inaccurate estimations and how proposed approaches can assist practitioners is essential. However, prior systematic literature reviews (SLR) only focus on the estimation practices (e.g., [26, 127]) and the effort estimation approaches (e.g., [6]). Aim: We aim to identify themes of reasons for inaccurate estimations and classify approaches to improve effort estimation. Method: We conducted an SLR and identified the key themes and a taxonomy. Results: The reasons for inaccurate estimation are related to information quality, team, estimation practice, project management, and business influences. The effort estimation approaches were the most investigated in the literature, while only a few aim to support the effort estimation process. Yet, few automated approaches are at risk of data leakage and indirect validation scenarios. Recommendations: Practitioners should enhance the quality of information for effort estimation, potentially by adopting an automated approach. Future research should aim to improve the information quality, while avoiding data leakage and indirect validation scenarios.

The upcoming Beyond 5G (B5G) and 6G networks are expected to provide enhanced capabilities such as ultra-high data rates, dense connectivity, and high scalability. It opens many possibilities for a new generation of services driven by Artificial Intelligence (AI) and billions of interconnected smart devices. However, with this expected massive upgrade, the privacy of people, organisations, and states is becoming a rising concern. The recent introduction of privacy laws and regulations for personal and non-personal data signals that global awareness is emerging in the current privacy landscape. Yet, many gaps need to be identified in the case of two data types. If not detected, they can lead to significant privacy leakages and attacks that will affect billions of people and organisations who utilise B5G/6G. This survey is a comprehensive study of personal and non-personal data privacy in B5G/6G to identify the current progress and future directions to ensure data privacy. We provide a detailed comparison of the two data types and a set of related privacy goals for B5G/6G. Next, we bring data privacy issues with possible solutions. This paper also provides future directions to preserve personal and non-personal data privacy in future networks.

Tiny Machine Learning (TinyML) is an emerging technology proposed by the scientific community for developing autonomous and secure devices that can gather, process, and provide results without transferring data to external entities. The technology aims to democratize AI by making it available to more sectors and contribute to the digital revolution of intelligent devices. In this work, a classification of the most common optimization techniques for Neural Network compression is conducted. Additionally, a review of the development boards and TinyML software is presented. Furthermore, the work provides educational resources, a classification of the technology applications, and future directions and concludes with the challenges and considerations.

In recent years, advanced machine learning and artificial intelligence techniques have gained popularity due to their ability to solve problems across various domains with high performance and quality. However, these techniques are often so complex that they fail to provide simple and understandable explanations for the outputs they generate. To address this issue, the field of explainable artificial intelligence has recently emerged. On the other hand, most data generated in different domains are inherently structural; that is, they consist of parts and relationships among them. Such data can be represented using either a simple data-structure or form, such as a vector, or a complex data-structure, such as a graph. The effect of this representation form on the explainability and interpretability of machine learning models is not extensively discussed in the literature. In this survey paper, we review efficient algorithms proposed for learning from inherently structured data, emphasizing how their representation form affects the explainability of learning models. A conclusion of our literature review is that using complex forms or data-structures for data representation improves not only the learning performance, but also the explainability and transparency of the model.

Social recommender systems (SocialRS) simultaneously leverage the user-to-item interactions as well as the user-to-user social relations for the task of generating item recommendations to users. Additionally exploiting social relations is clearly effective in understanding users’ tastes due to the effects of homophily and social influence. For this reason, SocialRS has increasingly attracted attention. In particular, with the advance of graph neural networks (GNN), many GNN-based SocialRS methods have been developed recently. Therefore, we conduct a comprehensive and systematic review of the literature on GNN-based SocialRS.

In this survey, we first identify 84 papers on GNN-based SocialRS after annotating 2,151 papers by following the PRISMA framework (preferred reporting items for systematic reviews and meta-analyses). Then, we comprehensively review them in terms of their inputs and architectures to propose a novel taxonomy: (1) input taxonomy includes 5 groups of input type notations and 7 groups of input representation notations; (2) architecture taxonomy includes 8 groups of GNN encoder notations, 2 groups of decoder notations, and 12 groups of loss function notations. We classify the GNN-based SocialRS methods into several categories as per the taxonomy and describe their details. Furthermore, we summarize benchmark datasets and metrics widely used to evaluate the GNN-based SocialRS methods. Finally, we conclude this survey by presenting some future research directions. GitHub repository with the curated list of papers are available at https://github.com/claws-lab/awesome-GNN-social-recsys.