Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Feizi, Aarash"'
Recent advances in parameter-efficient fine-tuning methods, such as Low Rank Adaptation (LoRA), have gained significant attention for their ability to efficiently adapt large foundational models to various downstream tasks. These methods are apprecia
Externí odkaz:
http://arxiv.org/abs/2410.17358
We propose Guided Positive Sampling Self-Supervised Learning (GPS-SSL), a general method to inject a priori knowledge into Self-Supervised Learning (SSL) positive samples selection. Current SSL methods leverage Data-Augmentations (DA) for generating
Externí odkaz:
http://arxiv.org/abs/2401.01990
Autor:
Pelrine, Kellin, Imouza, Anne, Yang, Zachary, Tian, Jacob-Junqi, Lévy, Sacha, Desrosiers-Brisebois, Gabrielle, Feizi, Aarash, Amadoro, Cécile, Blais, André, Godbout, Jean-François, Rabbany, Reihaneh
A large number of studies on social media compare the behaviour of users from different political parties. As a basic step, they employ a predictive model for inferring their political affiliation. The accuracy of this model can change the conclusion
Externí odkaz:
http://arxiv.org/abs/2308.13699
In this paper, we propose revisited versions for two recent hotel recognition datasets: Hotels50K and Hotel-ID. The revisited versions provide evaluation setups with different levels of difficulty to better align with the intended real-world applicat
Externí odkaz:
http://arxiv.org/abs/2207.10200
Learning low-dimensional representations for entities and relations in knowledge graphs using contrastive estimation represents a scalable and effective method for inferring connectivity patterns. A crucial aspect of contrastive learning approaches i
Externí odkaz:
http://arxiv.org/abs/2009.11355