Representation Learning via Variational Bayesian Networks

Oren Barkan, Avi Caciularu, Idan Rejwan, Ori Katz, Jonathan Weill, Itzik Malkiel, Noam Koenigstein

פרסום מחקרי: פרק בספר / בדוח / בכנספרסום בספר כנסביקורת עמיתים


We present Variational Bayesian Network (VBN) - a novel Bayesian entity representation learning model that utilizes hierarchical and relational side information and is particularly useful for modeling entities in the "long-tail'', where the data is scarce. VBN provides better modeling for long-tail entities via two complementary mechanisms: First, VBN employs informative hierarchical priors that enable information propagation between entities sharing common ancestors. Additionally, VBN models explicit relations between entities that enforce complementary structure and consistency, guiding the learned representations towards a more meaningful arrangement in space. Second, VBN represents entities by densities (rather than vectors), hence modeling uncertainty that plays a complementary role in coping with data scarcity. Finally, we propose a scalable Variational Bayes optimization algorithm that enables fast approximate Bayesian inference. We evaluate the effectiveness of VBN on linguistic, recommendations, and medical inference tasks. Our findings show that VBN outperforms other existing methods across multiple datasets, and especially in the long-tail.

שפה מקוריתאנגלית
כותר פרסום המארחCIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management
מוציא לאורAssociation for Computing Machinery
מספר עמודים11
מסת"ב (אלקטרוני)9781450384469
מזהי עצם דיגיטלי (DOIs)
סטטוס פרסוםפורסם - 26 אוק׳ 2021
אירוע30th ACM International Conference on Information and Knowledge Management, CIKM 2021 - Virtual, Online, אוסטרליה
משך הזמן: 1 נוב׳ 20215 נוב׳ 2021

סדרות פרסומים

שםInternational Conference on Information and Knowledge Management, Proceedings


כנס30th ACM International Conference on Information and Knowledge Management, CIKM 2021
עירVirtual, Online

הערה ביבליוגרפית

Publisher Copyright:
© 2021 ACM.

טביעת אצבע

להלן מוצגים תחומי המחקר של הפרסום 'Representation Learning via Variational Bayesian Networks'. יחד הם יוצרים טביעת אצבע ייחודית.

פורמט ציטוט ביבליוגרפי