24 papers · ranked by Valyu relevance
Jian Wang, Yourui Huangfu, Rong Li, Yiqun Ge + 1 more
—The wireless network is undergoing a trend from "connection of things" to "connection of intelligence". With data spread over the communication networks and computing capability enhanced on the devices, distributed learning becomes a hot topic in both industrial and academic communities. Man y frameworks, such as…
Leonardo Agueci, N Alex Cayco-Gajic
Adaptation is a fundamental aspect of motor learning. Intelligent systems must adapt to perturbations in the environment while simultaneously maintaining stable memories. Classic work has argued that this trade-off could be resolved by complementary learning systems operating at different speeds; yet the mechanisms…
Long Bao Le, Marcel Hussing, Eric Eaton
This work studies the intersection of continual and federated learning, in which independent agents face unique tasks in their environments and incrementally develop and share knowledge. We introduce a mathematical framework capturing the essential aspects of distributed continual learning, including agent model and…
Haotian Li
Machine learning and deep learning are novel and trending approaches to solving real-world scientific problems. Graph machine learning is dedicated to performing learning methods, such as graph neural networks, on non-Euclidean data such as graphs. Molecules, with their natural graph structures, could be analyzed by…
Mohamed Amine Legheraba, Stefan Galkiewicz, Maria Gradinariu Potop-Butucaru, Sébastien Tixeuil
Decentralized learning enhances privacy, scalability, and fault tolerance by distributing data and computation across nodes. A popular approach is Federated learning, which relies on a central aggregator, yet faces challenges such as server vulnerabilities, scalability issues, privacy risks and most importantly, the…
Mohammad Dehghani, Zahra Yazdanparast
Artificial intelligence has made remarkable progress in handling complex tasks, thanks to advances in hardware acceleration and machine learning algorithms. However, to acquire more accurate outcomes and solve more complex issues, algorithms should be trained with more data. Processing this huge amount of data could be…
T. V. Nguyen, M. A. Dakka, S. M. Diakiw, M. D. VerMilyea + 3 more
Training on multiple diverse data sources is critical to ensure unbiased and generalizable AI. In healthcare, data privacy laws prohibit data from being moved outside the country of origin, preventing global medical datasets being centralized for AI training. Data-centric, cross-silo federated learning represents a…
Bishal Thapaliya, Riyasat Ohib, Eloy Geenjar, Jingyu Liu + 2 more
Recent advancements in neuroimaging have led to greater data sharing among the scientific community. However, institutions frequently maintain control over their data, citing concerns related to research culture, privacy, and accountability. This creates a demand for innovative tools capable of analyzing amalgamated…
Ji Liu, Daxiang Dong, Xi Wang, An Qin + 4 more
'Patrick Valduriez' 'Dejing Dou' 'Dianhai Yu'] Although more layers and more parameters generally improve the accuracy of the models, such big models generally have high computational complexity and require big memory, which exceed the capacity of small devices for inference and incurs long training time. In addition…
Julie Y. L. Chow, Hilary J. Don, Ben Colagiuri, Evan J. Livesey
Associative learning models have traditionally simplified contingency learning by relying on binary classification of cues and outcomes, such as administering a medical treatment (or not) and observing whether the patient recovered (or not). While successful in capturing fundamental learning phenomena across human and…
Yasas Supeksala, Dinh C. Nguyen, Ming Ding, Thilina Ranbaduge + 4 more
'Calson Chua' 'Jun Zhang' 'Jun Li' 'H. Vincent Poor'] YASAS SUPEKSALA, Swinburne University of Technology, Australia DINH C. NGUYEN, Purdue University, USA MING DING, DATA61-CSIRO, Australia THILINA RANBADUGE, DATA61-CSIRO, Australia CALSON CHUA, Swinburne University of Technology, Australia JUN ZHANG, Swinburne…
Authors not listed
Machine olfaction—the artificial replication of the sense of smell—faces significant challenges due to the absence of large, standardized training datasets. Unlike vision, language, and audio models, which benefit from extensive corpora such as ImageNet, GLUE, and AudioSet, olfaction lacks scaled equivalents and…
Swier Garst, Julian Dekker, Marcel Reinders
Federated learning is an upcoming machine learning paradigm which allows data from multiple sources to be used for training of classifiers without the data leaving the source it originally resides. This can be highly valuable for use cases such as medical research, where gathering data at a central location can be…
Julie Y. L. Chow, Hilary J. Don, Ben Colagiuri, Evan J. Livesey
Associative learning models have traditionally simplified contingency learning by relying on binary classification of cues and outcomes, such as administering a medical treatment (or not) and observing whether the patient recovered (or not). While successful in capturing fundamental learning phenomena across human and…
Swier Garst, Julian Dekker, Marcel Reinders
Federated learning is an upcoming machine learning paradigm which allows data from multiple sources to be used for training of classifiers without the data leaving the source it originally resides. This can be highly valuable for use cases such as medical research, where gathering data at a central location can be…
Zhi-Hua Zhou
This article proposes `CoRE-learning' which introduces the `time-sharing' concept and enables `resource scheduling' in intelligent supercomputing facilities to be considered in machine learning theory for the first time.
Qi Zhou, Yantao Yu, Jingxiao Ma, Mohammad S. Obaidat + 4 more
In practical deployments of decentralized federated learning (FL) in Internet of Things (IoT) environments, the non-independent and identically distributed (Non-IID) nature of client-local data limits model performance. Furthermore, concept drift further exacerbates complexity and introduces temporal uncertainty that…
Younghwan Jeong, Taeyoon Kim, Francisco J. González-Castaño
Federated learning (FL) is a promising collaborative learning approach in edge computing, reducing communication costs and addressing the data privacy concerns of traditional cloud-based training. Owing to this, diverse studies have been conducted to distribute FL into industry. However, there still remain the…
Magne V. Aarset, Leiv Kåre Johannessen
When analyzing learning, focus has traditionally been on the teacher, but has in the recent decades slightly moved toward the learner. This is also reflected when supporting systems, both computer-based and more practical equipment, has been introduced. Seeing learning as an integration of both an internal…
Qi Chang, Zhennan Yan, Mu Zhou, Hui Qu + 7 more
Overcoming barriers on the use of multi-center data for medical analytics is challenging due to privacy protection and data heterogeneity in the healthcare system. In this study, we propose the Distributed Synthetic Learning (DSL) architecture to learn across multiple medical centers and ensure the protection of…
Authors not listed
Next Generation Risk Assessment (NGRA) promotes animal-free, exposure-informed, and hypothesis-driven approaches to chemical safety assessment. In silico tools, such as quantitative structure-activity relationship (QSAR) models, are valuable new approach methodologies (NAMs) for use in NGRA. However, the practical…
Junjie Hu, Xiangyu Li, Dan-Dan Liu, Shiyi Wang + 3 more
The combination of parametric quantum circuits and density matrix coding can significantly reduce the number of parameters in artificial neural networks. The reduction in the number of model parameters helps to improve the commu- nication efficiency when training deep learning models under federated learning…
Authors not listed
Large Language Models (LLMs) based on transformer architectures excel at internet-scale tasks. However, real-world scientific scenarios—such as synthetic chemistry laboratories and autonomous experimental setups—typically involve incremental data generation in batches as new chemical reactions are conducted, unlike…
Authors not listed
Machine learning models are transforming data-driven research across scientific disciplines, yet their deployment as accessible and reliable web services remains a significant challenge. We introduce the NERDD framework, a scalable, maintainable, and secure microservices platform designed to support the sustainable…