Descripción del proyecto
Mejorar el aprendizaje automático con modelos colaborativos
A medida que los modelos de aprendizaje automático se hacen más complejos, entrenarlos consume cada vez más recursos. Si a ello se añade la naturaleza en constante evolución de los datos del mundo real, los modelos deben adaptarse continuamente, lo que a menudo exige un reciclaje completo con conjuntos de datos nuevos. Este método aumenta las emisiones de CO2 y el consumo de energía, y consolida el progreso en el seno de las grandes empresas del sector. Con esta idea en mente, el equipo del proyecto CollectiveMinds, financiado por el CEI, establecerá una red de colaboración de modelos especializados que aprenden unos de otros, lo que reducirá la necesidad de un reciclaje completo. Al descentralizar el conocimiento y permitir actualizaciones independientes, promete un desarrollo más sostenible de la inte (IA). Con aplicaciones en la salud y la investigación científica, en CollectiveMinds se pretende democratizar el aprendizaje automático, lo que fomenta la cooperación y la sostenibilidad en un mundo en evolución.
Objetivo
Machine learning models are growing larger and more complex, making training increasingly resource-demanding. Concurrently, our world, and hence the training data is perpetually evolving. This requires continual model updating or retraining to address changing training data. Presently, the most reliable course to handle such distribution shifts is to retrain models from scratch on new training data. This results in substantial resource usage, increased CO2 footprint, elevated energy consumption, and limits the decisive ML progress to large-scale industry players.
Imagine a world in which models help each other learn. When the data distribution changes, a complete retraining of models could be avoided if the new model could learn from the outdated one by using reliable and provably effective methods. Furthermore, the convention of relying on large, versatile monolithic models could then give way to a consortium of smaller specialized models, with each contributing its specific domain knowledge when needed. By encouraging this form of decentralization, we could reduce resource consumption as the individual components can be updated independently of each other.
Drawing on groundbreaking research in distributed ML model training, CollectiveMinds aspires to design adaptable ML models. These models can effectively manage updates in training data and task modifications, while also enabling efficient knowledge exchange across various models, thereby fostering widescale collaborative learning and constructing a sustainable framework for collaborative machine intelligence.
This initiative could revolutionize sectors like healthcare, where there is limited training data, and trustworthy AI that demands guarantees on data ownership and control. Furthermore, it could foster improved collaborative research within the realm of science. CollectiveMinds embodies a significant paradigm shift towards democratizing ML, focusing on cooperative intellectual efforts.
Palabras clave
Programa(s)
- HORIZON.1.1 - European Research Council (ERC) Main Programme
Convocatoria de propuestas
(se abrirá en una nueva ventana) ERC-2024-COG
Consulte otros proyectos de esta convocatoriaRégimen de financiación
HORIZON-ERC -Institución de acogida
66123 Saarbrucken
Alemania