1 code implementation • 28 May 2023 • Edoardo D'Amico, Aonghus Lawlor, Neil Hurley
The use of graph convolution in the development of recommender system algorithms has recently achieved state-of-the-art results in the collaborative filtering task (CF).
1 code implementation • 28 Mar 2023 • Edoardo D'Amico, Khalil Muhammad, Elias Tragos, Barry Smyth, Neil Hurley, Aonghus Lawlor
We propose the construction of an item-item graph through a weighted projection of the bipartite interaction network and to employ convolution to inject higher order associations into item embeddings, while constructing user representations as weighted sums of the items with which they have interacted.
1 code implementation • 12 Apr 2021 • Giovanni Gabbolini, Edoardo D'Amico, Cesare Bernardis, Paolo Cremonesi
In this paper we question the reliability of the embeddings learned by Matrix Factorization (MF).