Issues deriving from the opaque behaviour of prediction-effective, yet non-interpretable, machine learning predictors are being studied and analysed since many decades. One of the main research branches consists of adopting anyway the unintelligible models, thanks to their predictive performance, but queueing to the learning workflow a dedicated technique aimed at post-hoc extracting human-interpretable

Assessment is essential to educational system. Automatic grading reduces the time and effort taken by tutors to assess the answers written by the students. To understand recent computational methods used for automatic grading, a review has been conducted. 4084 papers were initially identified using a keyword search. After filtering, the number was reduced to 57. It was found that statistical models

Parallel applications often use MPI processes and OpenMP threads. Those parallel execution models, multi-process and multi-thread, were invented to increase efficiency on uniprocessor systems. In the multi-process approach, each process’s isolated address space may make communication expensive; in the multi-thread design, shared variables may cause access conflicts and stall executions. Processes or

Relation extraction (RE) is critical in information extraction (IE) and knowledge graph construction. RE aims to identify the semantic relations between entities from natural language texts. Traditional RE models often rely on many manually annotated training samples, which are limited when data is scarce. Therefore, exploring how to perform relation extraction under few-shot conditions has become

In an era of rapid technological advancements, digital twins are gaining attention in industry and research. These virtual representations of real-world entities, enabled by the Internet of Things (IoT), offer advanced simulation and analysis capabilities. Their application spans various sectors, from smart manufacturing to healthcare, highlighting their versatility. However, the rise of digital technologies

Within an Identity federation (IF) system, users gain access to multiple Service Providers (SPs) by submitting credentials issued by one or more Identity Providers (IdPs). Such Identity Federations (IFs) raise several privacy concerns: IdPs might track user activity, by recording the accessed services, and SPs might mismanage sensitive user attributes that comprise the submitted credentials. An extensive

This survey dives into Tabular Data Learning (TDL) using Graph Neural Networks (GNNs), a domain where deep learning-based approaches have increasingly shown superior performance in both classification and regression tasks compared to traditional methods. We highlight a critical gap in deep neural TDL: the underrepresentation of latent correlations among data instances and feature values. GNNs, with

As large language models (LLMs) grow increasingly sophisticated and pervasive, their application to various Artificial Intelligence for IT Operations (AIOps) tasks has garnered significant attention. However, a comprehensive understanding of the impact, potential, and limitations of LLMs in AIOps remains in its infancy. To address this gap, we conducted a detailed survey of LLM4AIOps, focusing on how

Recommender systems play a crucial role in tackling the challenge of information overload by delivering personalized recommendations based on individual user preferences. Deep learning techniques, such as RNNs, GNNs, and Transformer architectures, have significantly propelled the advancement of recommender systems by enhancing their comprehension of user behaviors and preferences. However, supervised

Medical image segmentation plays a crucial role in assisting clinicians with diagnosing critical medical conditions. In deep learning, few-shot learning methods aim to replicate human learning by leveraging fewer examples for determining a prediction for a novel class. Researchers in the medical imaging community have also explored novel methods for few-shot medical image segmentation, leveraging meta-learning

The concept of world models has garnered significant attention due to advancements in multimodal large language models such as GPT-4 and video generation models such as Sora, which are central to the pursuit of artificial general intelligence. This survey offers a comprehensive review of the literature on world models. Generally, world models are regarded as tools for either understanding the present

Massive Open Online Courses (MOOCs) have been proliferating, offering free or low-cost content for learners. Nevertheless, the certification rate of both free and paid courses has been low (between 4.5% - 13% and 1% - 3%, respectively). Thus, this study aims to survey MOOCs certification predictive models, synthesise results for a comprehensive and deep understanding of this field and explore how these

The literature on bandits has developed largely independently of advances in causal inference. Work in the last few years has started investigating the close connections between these two areas and that has led to fruitful ideas that have produced advances in bandit algorithms. We present the first survey focusing specifically on the intersection of these two areas. We first provide a taxonomy for

The growth of the Internet of Things (IoT) has provided significant advances in several areas of the industry, but security concerns have also increased due to this expansion. Many IoT devices are the target of cyber attacks due to various firmware, source code, and software vulnerabilities. In this context, static code analysis, leveraging various techniques, has emerged as an effective approach to

Rhetorical figures play a major role in everyday communication, making text and speech more interesting, memorable, or persuasive through their association between form and meaning. Computational detection of rhetorical figures plays an important part in thorough understanding of complex communication patterns. In this survey, we provide a comprehensive overview of computational approaches to lesser-known

With the global deployment of the fifth-generation (5G) mobile technology, a new era characterized by ultra-high data speeds, ultra-low latency, and massive connectivity has emerged. However, these advancements also introduce new security and privacy challenges. The integration of new technologies in 5G has fundamentally altered the network structure, rendering traditional security methods inadequate

The analysis of an author’s perspective on a given topic within text presents a challenging problem in natural language processing. Stance detection, or the identification of an author’s inclination either in favor, against, or neutral towards some target entity, is an important classification task in this context. Significant progress has been made in stance detection, especially facilitated by deep

Question answering (QA) systems are a leading and rapidly advancing field of natural language processing (NLP) research. One of their key advantages is that they enable more natural interactions between humans and machines, such as in virtual assistants or search engines. Over the past few decades, many QA systems have been developed to handle diverse QA tasks. However, the evaluation of these systems

Artificial Intelligence has become integral to intelligent drug discovery, with Graph Machine Learning (GML) emerging as a powerful structure-based method for modelling graph-structured biomedical data and investigating their properties. However, GML faces challenges such as limited interpretability and heavy dependency on abundant high-quality training data. On the other hand, knowledge-based methods

ChatGPT, a Large Language Model (LLM) maintained by OpenAI, has demonstrated a remarkable ability to seemingly comprehend and contextually generate text. Among its myriad applications, its capability to autonomously generate and analyze computer code stands out as particularly promising. This functionality has piqued substantial interest due to its potential to streamline the software development process

Recommender systems (RSs) have emerged as an effective strategy for dealing with information overload. Their importance is undeniable as they are widely adopted in various web applications, presenting the potential to solve various problems associated with the abundance of choices. In recent years, the literature has witnessed the proposal of numerous recommendation techniques, constantly seeking to

This survey is the first work on the current standard for lightweight cryptography, standardized in 2023. Lightweight cryptography plays a vital role in securing resource-constrained embedded systems such as deeply-embedded systems (implantable and wearable medical devices, smart fabrics, smart homes, and the like), radio frequency identification (RFID) tags, sensor networks, and privacy-constrained

The internet world has created an era where any device can interconnect with each other. Gathering intelligence from streaming data is challenging and can create wonders and valuable innovations for humanity. The shortcomings of connectivity due to the remote location of the cloud induce latency and performance issues in real-time. Thus, a traditional cloud may not be suitable for all applications

Object detection (OD) has become vital for numerous computer vision applications, but deploying it on resource-constrained internet of things (IoT) devices presents a significant challenge. These devices, often powered by energy-efficient microcontrollers, struggle to handle the computational load of deep learning-based OD models. This issue is compounded by the rapid proliferation of IOT devices,

The treatment, monitoring and distribution of drinking water is an integral component of critical national infrastructure and therefore places continually increasing demands on Water Distribution Networks (WDNs). This domain and its sub-sectors face several major problems, namely climate change and drought-induced rises in water consumption from surface and underground reservoirs, in addition to the

The remarkable performance of large language models (LLMs) in content generation, coding, and common-sense reasoning has spurred widespread integration into many facets of society. However, integration of LLMs raises valid questions on their reliability and trustworthiness, given their propensity to generate hallucinations: plausible, factually-incorrect responses, which are expressed with striking

Event prediction is the ability of anticipating future events, i.e., future real-world occurrences, and aims to support the user in deciding on actions that change future events towards a desired state. An event prediction method learns the relation between features of past events and future events. It is applied to newly observed events to predict corresponding future events that are evaluated with

This review study explores the theoretical foundations, evolution, applications, and future potential of Kolmogorov-Arnold Networks (KAN), a neural network model inspired by the Kolmogorov-Arnold representation theorem. KANs set themselves apart from traditional neural networks by employing learnable, spline-parameterized functions rather than fixed activation functions, allowing for flexible and interpretable

With the advent of Large Vision-Language Models (LVLMs), new attack vectors, such as cognitive bias, prompt injection, and jailbreaking, have emerged. Understanding these attacks promotes system robustness improvement and neural networks demystification. However, existing surveys often target attack taxonomy and lack in-depth analysis like 1) unified insights into adversariality, transferability, and

In today’s digital world, GenAI is becoming increasingly prevalent by enabling unparalleled content generation capabilities for a wide range of advanced applications. This surge in adoption has sparked a significant increase in demand for data-centric GenAI models spanning the distributed edge-cloud continuum, placing increasing demands on communication infrastructures, highlighting the necessity for

A significant challenge in training large language models (LLMs) as effective assistants is aligning them with human preferences. Reinforcement learning from human feedback (RLHF) has emerged as a promising solution. However, our understanding of RLHF is often limited to initial design choices. This paper analyzes RLHF through reinforcement learning principles, focusing on the reward model. It examines

Distributed software systems are pervasive today and they are increasingly developed/deployed to meet the growing needs for scalable computing. Given their critical roles in modern information infrastructures, assuring the quality of distributed software is crucial. As a fundamental methodology for software quality assurance in general, program analysis underlies a range of techniques and tools for

With the development of the Large Language Models (LLMs), a large range of LLM-based Text-to-SQL(Text2SQL) methods have emerged. This survey provides a comprehensive review of LLM-based Text2SQL studies. We first enumerate classic benchmarks and evaluation metrics. For the two mainstream methods, prompt engineering and finetuning, we introduce a comprehensive taxonomy and offer practical insights into

Performing software engineering (SE) tasks requires the activation of software developers’ brain neural networks. Electroencephalography (EEG) microstate analysis emerges as a promising neurophysiological method to investigate the spatiotemporal dynamics of brain networks at high temporal resolution. An EEG microstate represents a unique topography of electric potentials over the multichannel EEG records

Graph deep learning methods have become popular tools to process collections of correlated time series. Unlike traditional multivariate forecasting methods, graph-based predictors leverage pairwise relationships by conditioning forecasts on graphs spanning the time series collection. The conditioning takes the form of architectural inductive biases on the forecasting architecture, resulting in a family

Differential privacy (DP), a rigorously quantifiable privacy preservation technique, has found widespread application within the domain of machine learning. As DP techniques are implemented in machine learning algorithms, a significant and intricate trade-off between privacy and utility emerges, garnering extensive attention from researchers. In the pursuit of striking a delicate equilibrium between

This survey addresses the crucial issue of factuality in Large Language Models (LLMs). As LLMs find applications across diverse domains, the reliability and accuracy of their outputs become vital. We define the “factuality issue” as the probability of LLMs to produce content inconsistent with established facts. We first delve into the implications of these inaccuracies. Subsequently, we analyze the

Remaining a dominant force in Internet traffic, video streaming captivates end users, service providers, and researchers. This paper takes a pragmatic approach to reviewing recent advances in the field by focusing on the prevalent streaming paradigm that involves delivering long-form two-dimensional videos over the best-effort Internet with client-side adaptive bitrate (ABR) algorithms and assistance

Over the past decade, the integration of electromyography (EMG) techniques with machine learning has significantly advanced prosthetic device control. Researchers have developed sophisticated deep learning classifiers for gesture recognition and created EMG controllers capable of simultaneous proportional control across multiple degrees of freedom. However, the increasing complexity of these machine

Recommender systems play a pivotal role in helping users navigate a vast selection of products and services. On online platforms, users have the opportunity to share feedback in various modes, such as numerical ratings, textual reviews, and likes/dislikes. Traditional recommendation systems rely on users’ explicit ratings or implicit interactions (e.g., likes, clicks, shares, and saves) to learn user

Unmanned Aerial Vehicles (UAVs) have gained significant attention in recent years for their potential applications in surveillance, monitoring, search and rescue, and mapping. However, efficient and optimal path planning remains a key challenge for UAV navigation. This survey paper reviews various UAV path planning algorithms, encompassing Sampling-Based techniques, Potential Field methods, Bio-Inspired

The literature on machine learning in the context of data streams is vast and growing. This indicates not only an ongoing interest, but also an ongoing need for a synthesis of new developments in this area. Here we reformulate the definitions of supervised data-stream learning, alongside consideration of contemporary concept drift and temporal dependence. Equipped with this, carry out a fresh discussion

With the development of mobile technologies, users can easily access Online social networks (OSNs), consequently, massive contents including personal experiences, observations, or opinions are generated online. These contents are being shared and exchanged in OSNs, which have a significant influence on the minds of people toward politics, societies, economics, etc. In this case, sentiment diffusion

Gaze input offers strong potential for creating intuitive and engaging user interfaces, but remains constrained by inherent limitations in accuracy and precision. Although extensive research has explored gaze-based interaction over the past three decades, a systematic framework that fully captures the diversity of gaze interaction techniques is still lacking. To address this gap, we present a novel

Pain assessment poses unique challenges due to its subjective and multifaceted nature, often requiring the integration of various sensor modalities. This review aims to provide a comprehensive overview of recent research focused specifically on acute pain assessment, with specific attention to: (a) identifying combinations of sensor modalities utilised for pain assessment, (b) exploring methods for

In the ongoing network cybersecurity arms race, the defenders face a significant disadvantage as they must detect and counteract every attack. Conversely, the attacker only needs to succeed once to achieve their goal. To balance the odds, Autonomous Cyber Network Defence (ACND) employs autonomous agents for proactive and intelligent cyber-attack response. This article surveys the state of the art of

Expert Team Formation is the search for gathering a team of experts who are expected to collaboratively work towards accomplishing a given project, a problem that has historically been solved in a variety of ways, including manually in a time-consuming and bias-filled manner, and algorithmically within disciplines like social sciences and management. In the present effort, while providing a taxonomy

Artificial Intelligence (AI) is transforming industries, offering new opportunities to manage and enhance innovation. However, these advancements bring significant challenges for scientists and businesses, with one of the most critical being the ‘trustworthiness” of AI systems. A key requirement of trustworthiness is transparency , closely linked to explicability . Consequently, the exponential growth

Facial expressions convey human emotions and can be categorized into macro-expressions (MaEs) and micro-expressions (MiEs) based on duration and intensity. While MaEs are voluntary and easily recognized, MiEs are involuntary, rapid, and can reveal concealed emotions. The integration of facial expression analysis with Internet-of-Thing (IoT) systems has significant potential across diverse scenarios

This is a comprehensive survey of the applications of causal inference in the Banking, Financial Services and Insurance (BFSI) domain based on 45 papers published from 1992 to 2023. It categorizes papers into (i) Banking and risk management (ii) Finance (covering investment, asset and portfolio management; behavioral finance and time series), (iii) Financial markets and (iv) Insurance. Exploring methods

Skiplists have become prevalent in systems. The main advantages of skiplists are their simplicity and ease of implementation, and the ability to support operations in the same asymptotic complexities as their tree-based counterparts. In this survey, we explore skiplists and their many variants. We highlight many scenarios about how skiplists are useful, and how they fit well in these usage scenarios

Face Recognition Systems (FRS) are critical and essential components for user authentication via biometrics. To name a few, baking, e-Commerce, and border control are entities propelling their progress. These are of immense importance due to their economic and social relevance. FRS widespread usage leads to security vulnerabilities that need to be identified and mitigated. This paper provides a comprehensive

Rapid advancements in Machine Learning (ML) introduce unique maintainability and scalability challenges. Our research addresses the evolving challenges and identifies ML maintainability and scalability solutions by conducting a thorough literature review of over 17,000 papers, ultimately refining our focus to 124 relevant sources that meet our stringent selection criteria. We present a catalogue of

Root cause localization is the process of monitoring system behavior and analyzing fault patterns from behavioral data. It is applicable in software development, network operations, and cloud computing. However, with the advent of microservice architectures and cloud-native technologies, root cause localization becomes an arduous task. Frequent updates in systems result in large-scale data and complex

Time-sensitive networking (TSN) has been recognized as one of the key enabling technologies for Industry 4.0 and has been deployed in many mission- and safety-critical applications e.g., industry automation, automotive and aerospace systems. Given the stringent real-time requirements of these applications, the Time-Aware Shaper (TAS) draws special attention among TSN’s many traffic shapers due to its

Conformal prediction (CP), a distribution-free uncertainty quantification (UQ) framework, reliably provides valid predictive inference for black-box models. CP constructs prediction sets or intervals that contain the true output with a specified probability. However, modern data science’s diverse modalities, along with increasing data and model complexity, challenge traditional CP methods. These developments

Electroencephalography (EEG) is a non-invasive technique to record bioelectrical signals. Integrating supervised deep learning techniques with EEG signals has recently facilitated automatic analysis across diverse EEG-based tasks. However, the label issues of EEG signals have constrained the development of EEG-based deep models. Obtaining EEG annotations is difficult and requires domain experts to

Machine Translation (MT) revolutionizes cross-lingual communication but is prone to errors, necessitating thorough evaluation for enhancement. Translation quality can be assessed by humans and automatic evaluation metrics. Human evaluation, though valuable, is costly and subject to limitations in scalability and consistency. While automated metrics supplement manual evaluations, this field still has

Large Language Models (LLMs) have demonstrated remarkable effectiveness across various domain-specific applications. However, which fundamental capabilities most contribute to their success in different domains remains unclear. This uncertainty complicates LLM evaluation, as existing benchmark-based assessments often fail to capture their real-world performance, where the required capabilities may

Security Application Programming Interfaces (APIs) are crucial for ensuring software security. However, their misuse introduces vulnerabilities, potentially leading to severe data breaches and substantial financial loss. Complex API design, inadequate documentation, and insufficient security training often lead to unintentional misuse by developers. The software security community has devised and evaluated