תקציר
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 מקורית | אנגלית |
---|---|
כותר פרסום המארח | CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management |
מוציא לאור | Association for Computing Machinery |
עמודים | 78-88 |
מספר עמודים | 11 |
מסת"ב (אלקטרוני) | 9781450384469 |
מזהי עצם דיגיטלי (DOIs) | |
סטטוס פרסום | פורסם - 26 אוק׳ 2021 |
אירוע | 30th ACM International Conference on Information and Knowledge Management, CIKM 2021 - Virtual, Online, אוסטרליה משך הזמן: 1 נוב׳ 2021 → 5 נוב׳ 2021 |
סדרות פרסומים
שם | International Conference on Information and Knowledge Management, Proceedings |
---|
כנס
כנס | 30th ACM International Conference on Information and Knowledge Management, CIKM 2021 |
---|---|
מדינה/אזור | אוסטרליה |
עיר | Virtual, Online |
תקופה | 1/11/21 → 5/11/21 |
הערה ביבליוגרפית
Publisher Copyright:© 2021 ACM.