21 papers · ranked by Valyu relevance
Horia Magureanu, Naïri Usher
The widespread adoption of large-scale machine learning models in recent years highlights the need for distributed computing for efficiency and scalability. This work introduces a novel distributed machine learning paradigm – consensus learning – which combines classical ensemble methods with consensus protocols…
Kyle L. Crandall, Dustin J. Webb
As the complexity of our neural network models grow, so too do the data and computation requirements for successful training. One proposed solution to this problem is training on a distributed network of computational devices, thus distributing the computational and data storage loads. This strategy has already seen…
Chao Yu, Guozhen Tan, Hongtao Lv, Zhen Wang + 3 more
'Fenghui Ren'] Learning is an important capability of humans and plays a vital role in human society for forming beliefs and opinions. In this paper, we investigate how learning affects the dynamics of opinion formation in social networks. A novel learning model is proposed, in which agents can dynamically adapt their…
Albert B. Kao, Noam Miller, Colin Torney, Andrew Hartnett + 2 more
'Iain D. Couzin' 'Stefano Allesina'] Learning has been studied extensively in the context of isolated individuals. However, many organisms are social and consequently make decisions both individually and as part of a collective. Reaching consensus necessarily means that a single option is chosen by the group, even when…
Yafeng Pan, Xiaojun Cheng, Yi Hu
Theories of human learning converge on the view that individuals working together learn better than do those working alone. Little is known, however, about the neural mechanisms of learning through cooperation. We addressed this research gap by leveraging functional near-infrared spectroscopy (fNIRS) to record the…
Daniel R. Wong, Ziqi Tang, Nicholas C. Mew, Sakshi Das + 9 more
Pathologists can have complementary assessments and focus areas when identifying and labeling neuropathologies. A standardized approach would ideally draw on the expertise of the entire cohort. We present a deep learning (DL) framework that consistently labels cored, diffuse, and cerebral amyloid angiopathy (CAA)…
Zhanhong Jiang, Aditya Balu, Chinmay Hegde, Soumik Sarkar
In distributed machine learning, where agents collaboratively learn from diverse private data sets, there is a fundamental tension between consensus and optimality. In this paper, we build on recent algorithmic progresses in distributed deep learning to explore various consensus-optimality trade-offs over a fixed…
Haimonti Dutta, Ashwin Srinivasan
A particularly successful role for Inductive Logic Programming (ILP) is as a tool for discovering useful relational features for subsequent use in a predictive model. Conceptually, the case for using ILP to construct relational features rests on treating these features as functions, the automated discovery of which…
Andrea Kopp, Peter Hartog, Martin Šícho, Guillaume Godin + 1 more
The EUOS/SLAS challenge has its goal to develop reliable algorithms to predict solubility of small molecules experimentally measured aqueous solubility of 100k compounds. In total, hundred teams took part in the challenge to predict low, medium and highly soluble compounds as measured by nephelometry assay. This…
Jenny Smith, Sean K. Maden, David Lee, Ronald Buie + 3 more
Acute myeloid leukemia (AML) is a cancer of hematopoietic systems that poses high population burden, especially among pediatric populations. AML presents with high molecular heterogeneity, complicating patient risk stratification and treatment planning. While molecular and cytogenetic subtypes of AML are well…
Andreagiovanni Reina, Thomas Bose, Vaibhav Srivastava, James A. R. Marshall
It is usually assumed that information cascades are most likely to occur when an early but incorrect opinion spreads through the group. Here we analyse models of confidence-sharing in groups and reveal the opposite result: simple but plausible models of naïve Bayesian decision-making exhibit information cascades when…
Qianyi Chen, Wenyuan Shi, Dongyan Sui, Siyang Leng + 1 more
Information aggregation in distributed sensor networks has received significant attention from researchers in various disciplines. Distributed consensus algorithms are broadly developed to accelerate the convergence to consensus under different communication and/or energy limitations. Non-Bayesian social learning…
Antoine Lacour, Hamza Ibrahim, Andrea Volkamer, Anna K. H. Hirsch
In this study, we introduce DockM8, an innovative open-source platform designed for consensus virtual screening in drug design. Leveraging various docking algorithms and scoring functions, DockM8 provides a highly customizable workflow for structure-based virtual screening. In rigorous evaluations across the DEKOIS…
Francesco Farina
In this paper, we introduce the concept of collective learning (CL) which exploits the notion of collective intelligence in the field of distributed semi-supervised learning. The proposed framework draws inspiration from the learning behavior of human beings, who alternate phases involving collaboration, confrontation…
El Mahdi El Mhamdi, Sadegh Farhadkhani, Rachid Guerraoui, Arsany Guirguis + 2 more
'Arsany Guirguis' 'Lê Nguyên Hoang' 'Sébastien Rouault'] We study Byzantine collaborative learning, where n nodes seek to collectively learn from each others' local data. The data distribution may vary from one node to another. No node is trusted, and f < n nodes can behave arbitrarily. We prove that collaborative…
Yang Lou, Guanrong Chen
Naming game simulates the process of naming an objective by a population of agents organized in a certain communication network. By pair-wise iterative interactions, the population reaches consensus asymptotically. We study naming game with communication errors during pair-wise conversations, with error rates in a…
Mohammad Rostami, Soheil Kolouri, Kyungnam Kim, Eric Eaton
Lifelong machine learning methods acquire knowledge over a series of consecutive tasks, continually building upon their experience. Current lifelong learning algorithms rely upon a single learning agent that has centralized access to all data. In this paper, we extend the idea of lifelong learning from a single agent…
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…
Vishwa Goudar, Barbara Peysakhovich, David J. Freedman, Elizabeth A. Buffalo + 1 more
Learning-to-learn, a progressive speedup of learning while solving a series of similar problems, represents a core process of knowledge acquisition that draws attention in both neuroscience and artificial intelligence. To investigate its underlying brain mechanism, we trained a recurrent neural network model on…
Paul Francoeur, Daniel Penaherrera, David Koes
The immense size of chemical space, the relative scarcity of high quality data, and the cost of running experiments to accurately measure molecular properties makes active learning (AL) an attractive approach to efficiently explore the space and train high-quality models for molecular property prediction. While AL is…
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…