Bringing multi-modal multi-task federated foundation models to education domain: prospects and challenges

In recent years, advances in diagnosing and classifying diseases using machine learning (ML) have grown exponentially. However, due to the many privacy regulations regarding personal data, pooling together data from multiple sources and storing them in a single (centralized) location for traditional ML model training are often infeasible. Federated learning (FL), a collaborative learning paradigm, can sidestep this major pitfall by creating a global ML model that is trained by aggregating model weights from individual models that are separately trained on their own data silos, therefore avoiding most data privacy concerns. This study addresses the centralized data issue with FL by applying a novel DataWeightedFed architectural approach for effective fundus disease diagnosis from ophthalmic images. It includes a novel method for aggregating model weights by comparing the size of each model’s data and taking a dynamically weighted average of all the model’s weights. Experimental results showed a small average 1.85% loss in accuracy when training using FL compared to centralized ML model systems, a nearly 92% improvement over the conventional 55% accuracy loss. The obtained results demonstrate that this study’s FL architecture can maximize both privacy preservation and accuracy for ML in fundus disease diagnosis and provide a secure, collaborative ML model training solution within the eye healthcare space.

In recent years, to surmount the challenges of data sensitivity and data silos, federated learning (FL), a collaborative decentralized privacy preservation machine learning framework was proposed and rapidly became a current research hotspot. In this paper, we present an overview of FL workflow, as well as the communication overhead and privacy leakage problems associated with FL. In order to alleviate these two pain points, several corresponding solutions are presented in this paper along with their advantages and disadvantages. To reduce the communication overhead, this paper suggests three reliable approaches by reviewing related research including increasing the amount of computing on the edge side, model compression, and improving parallelism. To address the privacy concerns, this paper introduces three prevailing privacy preservation techniques: differential privacy, homomorphic encryption, and secure multiparty computation (SMC), and shows how to efficiently incorporate these privacy-preserving techniques into a federated learning framework by summarizing relevant literature. On the whole, this paper contributes to explaining the overall workflow of a FL framework and helps advance the understanding of FL in improving communication efficiency and enhancing privacy security.

Federated learning (FL) has arisen as an alternative to collecting large amounts of data in a central place to train a machine learning (ML) model. FL is privacy-friendly, allowing multiple parties to collaboratively train an ML model without exchanging or transmitting their training data. For this purpose, an aggregator iteratively coordinates the training process among parties, and parties simply share with the aggregator model updates, which contain information pertinent to the model such as neural network weights. Besides privacy, generalization has been another key driver for FL: parties who do not have enough data to train a good performing model by themselves can now engage in FL to obtain an ML model suitable for their tasks. Products and real applications in the industry and consumer space have demonstrated the power of this learning paradigm. Recently, foundation models have taken the AI community by storm, promising to solve the shortage of labeled data. A foundation model is a powerful model that can be recycled for a variety of use cases by applying techniques such as zero-shot learning and full or parameter-efficient fine tuning. The premise is that the amount of data required to fine tune a foundation model for a new task is much smaller than fully training a traditional model from scratch. The reason why this is the case is that a good foundation model has already learned relevant general representations, and thus, adapting it to a new task only requires a minimal number of additional samples. This raises the question: Is FL still alive in the era of foundation models? In this talk, I will address this question. I will present some use cases where FL is very much alive. In these use cases, finding a foundation model with a desired representation is difficult if not impossible. With this pragmatic point of view, I hope to shed some light into a real use case where disparate private data is available in isolation at different parties and where labels may be located at a single party that doesn’t have any other information, making it impossible for a single party to train a model on its own. Furthermore, in some vertically-partitioned scenarios, cleaning data is not an option due to privacy-related reasons and it is not clear how to apply foundation models. Finally, I will also go over a few other requirements that are often overlooked, such as unlearning of data and its implications for the lifecycle management of FL and systems based on foundation models.

Employee attrition is a critical challenge for organizations, impacting productivity, operational costs, and workforce stability. Traditional approaches to managing attrition rely on reactive strategies, often failing to provide predictive insights. The advent of Artificial Intelligence (AI) has transformed attrition management by enabling data-driven decision-making, predictive analytics, and proactive employee engagement.This research explores the role of AI in predicting and managing employee attrition through machine learning algorithms, natural language processing (NLP), and AI-driven sentiment analysis. AI models analyze vast datasets, including employee performance metrics, engagement surveys, and organizational culture indicators, to identify early warning signs of attrition. Predictive analytics empowers HR professionals to implement targeted retention strategies, enhance employee experience, and reduce voluntary turnover.Furthermore, AI-driven chatbots and virtual HR assistants contribute to employee satisfaction by offering personalized career development suggestions, real-time feedback, and mental well-being support. Explainable AI (XAI) frameworks ensure transparency in AI-driven decisions, fostering trust between employees and organizations. Despite AI’s potential, ethical concerns, data privacy, and algorithmic biases remain key challenges that require robust governance frameworks.This study provides a comprehensive analysis of AI applications in attrition management, highlighting case studies from multinational corporations that have successfully integrated AI for workforce retention. The findings underscore AI's transformative potential in HRM, enabling organizations to shift from reactive to proactive attrition management strategies. The paper concludes with future research directions on AI’s evolving role in predictive HR analytics and its integration with emerging technologies like blockchain and the metaverse for enhanced workforce planning.

This artilce aims to develop a differential private federated learning (FL) scheme with the least artificial noises added while minimizing the energy consumption of participating mobile devices. By observing that some communication efficient FL approaches and even the nature of wireless communications contribute to the differential privacy (DP) preservation of training data on mobile devices, in this paper, we propose to jointly leverage gradient compression techniques (i.e., gradient quantization and sparsification) and additive white Gaussian noises (AWGN) in wireless channels to develop a piggyback DP approach for FL over mobile devices. Even with the piggyback DP approach, information distortion caused by gradient compression and noise perturbation may slow down FL convergence, which in turn consumes more energy of mobile devices for local computing and model update communications. Thus, we theoretically analyze FL convergence and formulate an energy efficient FL optimization under piggyback DP, transmission power, and FL convergence constraints. Furthermore, we propose an efficient iterative algorithm where closed-form solutions for artificial DP noise and power control are derived. Extensive simulation and experimental results demonstrate the effectiveness of the proposed scheme in terms of energy efficiency and privacy preservation.

This systematic review explores the role of artificial intelligence (AI) and machine learning (ML) technologies in the diagnosis and treatment of thyroid cancers (TC), focusing on enhancing precision, risk assessment, and tailored care. By analyzing ten studies, the review highlights how AI and ML technologies, such as deep learning (DL) and computer-aided diagnostics (CAD), improve the accuracy of ultrasound imaging, risk stratification, and the detection of high-risk nodules. Despite advancements, challenges persist in transitioning to personalized care, including uneven prognostication and diagnostic uncertainty. The review evaluates the effectiveness of AI and ML compared to conventional methods, their ability to address diverse tumor characteristics, and their strengths and limitations in prognosis prediction. Findings suggest AI's potential in improving precision and risk assessment, but limitations such as inconsistent approaches and biases highlight the need for larger datasets and standardized procedures. Moreover, the review underscores the importance of interpretability and transparency in AI models and calls for further research to validate findings in clinical settings. Despite limitations and challenges, AI's transformative potential in TC management is evident, underscoring the need for ongoing investigation and integration into clinical practice.

Interest is growing in the potential of artificial intelligence (AI) chatbots and large language models like OpenAI's ChatGPT and Google's Gemini, particularly in dental education. To explore dental educators' perceptions of AI chatbots and large language models, specifically their potential benefits and challenges for dental education. A global cross-sectional survey was conducted in May-June 2023 using a 31-item online-questionnaire to assess dental educators' perceptions of AI chatbots like ChatGPT and their influence on dental education. Dental educators, representing diverse backgrounds, were asked about their use of AI, its perceived impact, barriers to using chatbots, and the future role of AI in this field. 428 dental educators (survey views = 1516; response rate = 28%) with a median [25/75th percentiles] age of 45 [37, 56] and 16 [8, 25] years of experience participated, with the majority from the Americas (54%), followed by Europe (26%) and Asia (10%). Thirty-one percent of respondents already use AI tools, with 64% recognising their potential in dental education. Perception of AI's potential impact on dental education varied by region, with Africa (4[4-5]), Asia (4[4-5]), and the Americas (4[3-5]) perceiving more potential than Europe (3[3-4]). Educators stated that AI chatbots could enhance knowledge acquisition (74.3%), research (68.5%), and clinical decision-making (63.6%) but expressed concern about AI's potential to reduce human interaction (53.9%). Dental educators' chief concerns centred around the absence of clear guidelines and training for using AI chatbots. A positive yet cautious view towards AI chatbot integration in dental curricula is prevalent, underscoring the need for clear implementation guidelines.

A large number of mobile devices, smart wearable devices, and medical and health sensors continue to generate massive amounts of data, making edge devices’ data explode and making it possible to implement data-driven artificial intelligence. However, the “data silos” and other issues still exist and need to be solved. Fortunately, federated learning (FL) can deal with “data silos” in the medical field, facilitating collaborative learning across multiple institutions without sharing local data and avoiding user concerns about data privacy. However, it encounters two main challenges in the medical field. One is statistical heterogeneity, also known as non-IID (non-independent and identically distributed) data, i.e., data being non-IID between clients, which leads to model drift. The second is limited labeling because labels are hard to obtain due to the high cost and expertise requirement. Most existing federated learning algorithms only allow for supervised training settings. In this work, we proposed a novel federated learning framework, MixFedGAN, to tackle the above issues in federated networks with dynamic aggregation and knowledge distillation. A dynamic aggregation scheme was designed to reduce the impact of current low-performing clients and improve stability. Knowledge distillation was introduced into the local generator model with a new distillation regularization loss function to prevent essential parameters of the global generator model from significantly changing. In addition, we considered two scenarios under this framework: complete annotated data and limited labeled data. An experimental analysis on four heterogeneous COVID-19 infection segmentation datasets and three heterogeneous prostate MRI segmentation datasets verified the effectiveness of the proposed federated learning method.

The rapid evolution of artificial intelligence (AI) continues to reshape how information is produced, shared, and accessed, raising urgent questions about equity, accountability, and fairness. This poster, inspired by the upcoming volume Assessing AI and Social Justice Intersections: Challenges and Opportunities, explores the intersection of AI and social justice, highlighting select forthcoming chapter content from real‐world experiences and challenges, community‐driven solutions, and varied theoretical and computational frameworks. It draws on diverse philosophical, methodological, ontological, and practice‐based perspectives to critically evaluate AI's potential both as a mechanism for empowerment and force capable of exacerbating existing inequalities. The poster provides multidisciplinary and international coverage of ethical frameworks, resistance strategies, educational applications, data autonomy, cultural competence, and equity in information systems design. Algorithmic oppressions in information retrieval, equitable implementation of AI in libraries and educational institutions, culturally responsive AI practices, and community‐driven AI initiatives are included.

Federated learning (FL) empowers a cohort of participating devices to contribute collaboratively to a global neural network model, ensuring that their training data remains private and stored locally. Despite its advantages in computational efficiency and privacy preservation, FL grapples with the challenge of non-IID (not independent and identically distributed) data from diverse clients, leading to discrepancies between local and global models and potential performance degradation. In this article, we propose FedGK, an innovative communication-efficient Group-Guided FL framework designed for heterogeneous data distributions. FedGK employs a localized-guided framework that enables the client to effectively assimilate key knowledge from teachers and peers while minimizing extraneous peer information in FL scenarios. We conduct an in-depth analysis of the dynamic similarities among clients over successive communication rounds and develop a novel clustering approach that accurately groups clients with diverse heterogeneities. We implement FedGK on public datasets with an innovative data transformation pattern called “cluster-shift non-IID”, which mirrors the more prevalent data distributions in real-world settings and could be grouped into clusters with similar data distributions. Extensive experimental results on public datasets demonstrate that the proposed approach FedGK improves accuracy by up to 32.89% and saves up to 53.33% communication cost over state-of-the-art baselines.

The properties of the blockchain are not suitable for the storage of sensitive privacy data, and the excellent characteristics of the blockchain will be seriously affected by the existence of massive amounts of data on the chain.To address the above issues, propose a Loosely Coupled Local Differential Privacy Blockchain Federated Learning method (LL-BCFL).First of all, a client selection mechanism is put forward to ensure honesty and positivity in joining the training client and the correct effectiveness of the final global model aggregation.Secondly, use federated learning to alleviate the 'data silos' phenomenon and achieve joint training of big data stored in distributed multi-parties.Additionally, a differential privacy method is introduced to act on federated learning networks to avoid inference attacks.Finally, the MNIST dataset was used to confirm the availability of the LL-BCFL method on balanced and unbalanced datasets.

<abstract> <p>Federated learning (FL) provides a collaborative framework that enables intelligent networking devices to train a shared model without the need to share local data. FL has been applied in communication networks, which offers the dual advantage of preserving user privacy and reducing communication overhead. Networking systems and FL are highly complementary. Networking environments provide critical support for data acquisition, edge computing capabilities, round communication/connectivity, and scalable topologies. In turn, FL can leverage capabilities to achieve learning adaptation, low-latency operation, edge intelligence, personalization, and, notably, privacy preservation. In our review, we gather relevant literature and open-source platforms that point out the feasibility of conducting experiments at the confluence of FL and intelligent networking. Our review is structured around key sections, including the introduction of FL concepts, the background of FL applied in networking, and experimental simulations covering networking for FL and FL for networking. Additionally, we delved into case studies showcasing FL potential in optimizing state-of-the-art network optimization objectives, such as learning performance, quality of service, energy, and cost. We also addressed the challenges and outlined future research directions that provide valuable guidance to researchers and practitioners in this trending field.</p> </abstract>

Artificial intelligence (AI) has, in the recent past, experienced a rebirth with the growth of generative AI systems such as ChatGPT and Bard. These systems are trained with billions of parameters and have enabled widespread accessibility and understanding of AI among different user groups. Widespread adoption of AI has led to the need for understanding how machine learning (ML) models operate to build trust in them. An understanding of how these models generate their results remains a huge challenge that explainable AI seeks to solve. Federated learning (FL) grew out of the need to have privacy-preserving AI by having ML models that are decentralized but still share model parameters with a global model. This study sought to examine the extent of development of the explainable AI field within the FL environment in relation to the main contributions made, the types of FL, the sectors it is applied to, the models used, the methods applied by each study, and the databases from which sources are obtained. A systematic search in 8 electronic databases, namely, Web of Science Core Collection, Scopus, PubMed, ACM Digital Library, IEEE Xplore, Mendeley, BASE, and Google Scholar, was undertaken. A review of 26 studies revealed that research on explainable FL is steadily growing despite being concentrated in Europe and Asia. The key determinants of FL use were data privacy and limited training data. Horizontal FL remains the preferred approach for federated ML, whereas post hoc explainability techniques were preferred. There is potential for development of novel approaches and improvement of existing approaches in the explainable FL field, especially for critical areas. OSF Registries 10.17605/OSF.IO/Y85WA; https://osf.io/y85wa.

The advancement of healthcare informatization has resulted in the exponential growth of patient data stored across various hospitals, laboratories, and clinical centers, properly integration and analysis of this data and use it for machine learning can help make medical processes more efficient. However, privacy regulations and institutional silos pose substantial barriers to collaborative research and centralized model training. Here, Federated Learning (FL) has surfaced as an innovative distributed learning approach, as it empowers institutions to jointly build models while safeguarding raw data privacy. This review outlines FL’s fundamentals and highlights its applications across multiple healthcare domains, including medical image analysis, clinical outcome prediction, and wearable health monitoring. The fundamental FL designs (horizontal FL, vertical FL, and split FL learning) and privacy-enhancing methods (safe aggregation, homomorphic encryption, and differential privacy) are discussed. Additionally, we also examine recent advances in adaptive privacy mechanisms, asynchronous updates and explainable AI to support clinical integration. The study concludes with a discussion of current limitations and future research directions, such as multimodal FL, personalized modeling, and edge-based computing.

Federated learning (FL) refers to a system of training and stabilizing local machine learning models at the global level by aggregating the learning gradients of the models. It reduces the concern of sharing the private data of participating entities for statistical analysis to be carried out at the server. It allows participating entities called clients or users to infer useful information from their raw data. As a consequence, the need to share their confidential information with any other entity or the central entity called server is eliminated. FL can be clearly interpreted as a privacy-preserving version of traditional machine learning and deep learning algorithms. However, despite this being an efficient distributed training scheme, the client’s sensitive information can still be exposed to various security threats from the shared parameters. Since data has always been a major priority for any user or organization, this article is primarily concerned with discussing the significant problems and issues relevant to the preservation of data privacy and the viability and feasibility of several proposed solutions in the FL context. In this work, we conduct a detailed study on FL, the categorization of FL, the challenges of FL, and various attacks that can be executed to disclose the users’ sensitive data used during learning. In this survey, we review and compare different privacy solutions for FL to prevent data leakage and discuss secret sharing (SS)-based security solutions for FL proposed by various researchers in concise form. We also briefly discuss quantum federated learning (QFL) and privacy-preservation techniques in QFL. In addition to these, a comparison and contrast of several survey works on FL is included in this work. We highlight the major applications based on FL. We discuss certain future directions pertaining to the open issues in the field of FL and finally conclude our work.