Scalable Probabilistic Matrix Factorization with Graph-­Based Priors

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

Abstrakti

In matrix factorization, available graph side-information may not be well suited for the matrix completion problem, having edges that disagree with the latent-feature relations learnt from the incomplete data matrix. We show that removing these contested edges improves prediction accuracy and scalability. We identify the contested edges through a highly-efficient graphical lasso approximation. The identification and removal of contested edges adds no computational complexity to state-of-the-art graph-regularized matrix factorization, remaining linear with respect to the number of non-zeros. Computational load even decreases proportional to the number of edges removed. Formulating a probabilistic generative model and using expectation maximization to extend graph-regularised alternating least squares (GRALS) guarantees convergence. Rich simulated experiments illustrate the desired properties of the resulting algorithm. On real data experiments we demonstrate improved prediction accuracy with fewer graph edges (empirical evidence that graph side-information is often inaccurate). A 300 thousand dimensional graph with three million edges (Yahoo music side-information) can be analyzed in under ten minutes on a standard laptop computer demonstrating the efficiency of our graph update.
AlkuperäiskieliEnglanti
OtsikkoProceedings of AAAI-20, AAAI Conference on Artificial Intelligence
KustantajaAAAI
Sivut5851-5858
Sivumäärä8
DOI - pysyväislinkit
TilaJulkaistu - 3 huhtikuuta 2020
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaAAAI Conference on Artificial Intelligence - New York, Yhdysvallat
Kesto: 7 helmikuuta 202012 helmikuuta 2020
Konferenssinumero: 34
https://aaai.org/Conferences/AAAI-20/

Julkaisusarja

NimiProceedings of the AAAI Conference on Artificial Intelligence
KustantajaAAAI Press
Numero4
Vuosikerta34
ISSN (painettu)2159-5399
ISSN (elektroninen)2374-3468

Conference

ConferenceAAAI Conference on Artificial Intelligence
LyhennettäAAAI
Maa/AlueYhdysvallat
KaupunkiNew York
Ajanjakso07/02/202012/02/2020
www-osoite

Sormenjälki

Sukella tutkimusaiheisiin 'Scalable Probabilistic Matrix Factorization with Graph-­Based Priors'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä