Search · four archives
Search · four archives
24 papers · ranked by Valyu relevance
Jialei Wang, Mladen Kolar, Nathan Srebro
We study the problem of distributed multitask learning with shared representation, where each machine aims to learn a separate, but related, task in an unknown shared low-dimensional subspaces, i.e. when the predictor matrix has low rank. We consider a setting where each task is handled by a different machine, with…
Sulin Liu, Sinno Jialin Pan, Qirong Ho
Multi-task learning aims to learn multiple tasks jointly by exploiting their relatedness to improve the generalization performance for each task. Traditionally, to perform multi-task learning, one needs to centralize data from all the tasks to a single machine. However, in many real-world applications, data of…
İnci M. Baytaş, Ming Yan, Anil K. Jain, Jiayu Zhou
—Many real-world machine learning applications involve several learning tasks which are inter-related. For example, in healthcare domain, we need to learn a predictive model of a certain disease for many hospitals. The models for each hospital may be different because of the inherent differences in the distributions of…
Peng Yang, Ping Li
Conventional online multi-task learning algorithms suffer from two critical limitations: 1) Heavy communication caused by delivering high velocity of sequential data to a central machine; 2) Expensive runtime complexity for building task relatedness. To address these issues, in this paper we consider a setting where…
Han Cao, Youcheng Zhang, Jan Baumbach, Paul R Burton + 10 more
Multitask learning allows the simultaneous learning of multiple ‘communicating’ algorithms. It is increasingly adopted for biomedical applications, such as the modeling of disease progression. As data protection regulations limit data sharing for such analyses, an implementation of multitask learning on geographically…
Jiani Li, Waseem Abbas, Xenofon Koutsoukos
Distributed multi-task learning provides significant advantages in multi-agent networks with heterogeneous data sources where agents aim to learn distinct but correlated models simultaneously. However, distributed algorithms for learning relatedness among tasks are not resilient in the presence of Byzantine agents. In…
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…
Borja Fernandez-Gauna, Ismael Etxeberria-Agiriano, Manuel Graña, Catalin Buiu
'Catalin Buiu'] Multi-Agent Reinforcement Learning (MARL) algorithms face two main difficulties: the curse of dimensionality, and environment non-stationarity due to the independent learning processes carried out by the agents concurrently. In this paper we formalize and prove the convergence of a Distributed Round…
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.
Liang Gao, Xu Lan, Haibo Mi, Dawei Feng + 2 more
Recently, deep learning has achieved state-of-the-art performance in more aspects than traditional shallow architecture-based machine-learning methods. However, in order to achieve higher accuracy, it is usually necessary to extend the network depth or ensemble the results of different neural networks. Increasing…
Huiguo Gao, Mengyuan Lee, Guanding Yu, Zhaolin Zhou + 1 more
As an emerging paradigm considering data privacy and transmission efficiency, decentralized learning aims to acquire a global model using the training data distributed over many user devices. It is a challenging problem since link loss, partial device participation, and non-independent and identically distributed…
Jilin Zhang, Hangdi Tu, Yongjian Ren, Jian Wan + 6 more
'Mingwei Li' 'Jue Wang' 'Lifeng Yu' 'Chang Zhao' 'Lei Zhang'] In order to utilize the distributed characteristic of sensors, distributed machine learning has become the mainstream approach, but the different computing capability of sensors and network delays greatly influence the accuracy and the convergence rate of…
Authors not listed
Equivariant graph neural networks have shown remarkable success in molecular property prediction, but their performance on novel molecular geometries remains limited without extensive training data. We present a computationally efficient approach to cross-geometry pretraining for molecular systems that improves…
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…
Jinho Park, Kwangsue Chung, Sergio Toral Marín
Various edge collaboration schemes that rely on reinforcement learning (RL) have been proposed to improve the quality of experience (QoE). Deep RL (DRL) maximizes cumulative rewards through large-scale exploration and exploitation. However, the existing DRL schemes do not consider the temporal states using a fully…
Hyeonseong Choi, Byung Hyun Lee, Se Young Chun, Jaehwan Lee + 1 more
'Elena Loli Piccolomini'] Modern deep neural networks cannot be often trained on a single GPU due to large model size and large data size. Model parallelism splits a model for multiple GPUs, but making it scalable and seamless is challenging due to different information sharing among GPUs with communication overhead.…
Nicola K Dinsdale, Mark Jenkinson, Ana IL Namburete
It is essential to be able to combine datasets across imaging centres to represent the breadth of biological variability present in clinical populations. This, however, leads to two challenges: first, an increase in non-biological variance due to scanner differences, known as the harmonisation problem, and, second…
Zhenglong Zhou, Dhairyya Singh, Marlie C. Tandoc, Anna C. Schapiro
Inferring relationships that go beyond our direct experience is essential for understanding our environment. This capacity requires either building representations that directly reflect structure across experiences as we encounter them, or computing the indirect relationships across experiences as the need arises.…
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…
Noah Lewis, Harshvardhan Gazula, Sergey M. Plis, Vince D. Calhoun
In this age of big data, large data stores allow researchers to compose robust models that are accurate and informative. In many cases, the data are stored in separate locations requiring data transfer between local sites, which can cause various practical hurdles, such as privacy concerns or heavy network load. This…
Authors not listed
This comprehensive review examines the evolution of autonomous materials synthesis laboratories that integrate artificial intelligence with advanced robotics to accelerate discovery. Traditional materials development pipelines typically require 10-20 years, but self-driving laboratories (SDLs) and Materials…
Derek van Tilborg, Helena Brinkmann, Emanuele Criscuolo, Luke Rossen + 2 more
Deep learning is becoming increasingly relevant in drug discovery, from de novo design to protein structure prediction and synthesis planning. However, it is often challenged by the small data regimes typical of certain drug discovery tasks. In such scenarios, deep learning approaches – which are notoriously…
David Buterez, Jon Paul Janet, Steven Kiddle, Pietro Liò
We investigate the potential of graph neural networks for transfer learning and improving molecular property prediction on sparse and expensive to acquire high-fidelity data by leveraging low-fidelity measurements as an inexpensive proxy for a targeted property ofinterest. This problem arises in discovery processes…
Nathan Frey, Ryan Soklaski, Simon Axelrod, Siddharth Samsi + 3 more
Massive scale, both in terms of data availability and computation, enables significant breakthroughs in key application areas of deep learning such as natural language processing (NLP) and computer vision. There is emerging evidence that scale may be a key ingredient in scientific deep learning, but the importance of…