no code implementations • 31 Mar 2023 • Georgios Papadopoulos, Fran Silavong, Sean Moran
Finding relevant and high-quality datasets to train machine learning models is a major bottleneck for practitioners.
no code implementations • 17 Feb 2023 • Xiaoying Zhi, Varun Babbar, Pheobe Sun, Fran Silavong, Ruibo Shi, Sean Moran
Our method enables pruning and training simultaneously, which saves energy in both the training and inference phases and avoids extra computational overhead from gating modules at inference time.
1 code implementation • 14 Dec 2022 • Sae Young Moon, Gregor Kerr, Fran Silavong, Sean Moran
Overall, API-Miner will allow developers to retrieve relevant OpenAPI specification components from a public or internal database in the early stages of the API development cycle, so that they can learn from existing established examples and potentially identify redundancies in their work.
1 code implementation • 19 Aug 2022 • Agathe Lherondelle, Varun Babbar, Yash Satsangi, Fran Silavong, Shaltiel Eloul, Sean Moran
This paper presents Topical, a novel deep neural network for repository level embeddings.
no code implementations • 11 May 2022 • Ruibo Shi, Lili Tao, Rohan Saphal, Fran Silavong, Sean J. Moran
We present CV4Code, a compact and effective computer vision method for sourcecode understanding.
no code implementations • 26 Apr 2022 • Shaltiel Eloul, Fran Silavong, Sanket Kamthe, Antonios Georgiadis, Sean J. Moran
We show that otherwise it is possible to directly recover all vectors in a mini-batch without any numerical optimisation due to the de-mixing nature of the cross entropy loss.
no code implementations • 25 Mar 2022 • Antonios Georgiadis, Varun Babbar, Fran Silavong, Sean Moran, Rob Otter
We demonstrate that the widely varying data quality on FL client nodes leads to a sub-optimal centralised FL model for COVID-19 chest CT image segmentation.
no code implementations • 5 Nov 2021 • Fran Silavong, Sean Moran, Antonios Georgiadis, Rohan Saphal, Robert Otter
Senatus also outperforms standard MinHash LSH by 29. 2\% F1 and 51. 02\emph{x} faster query time.