Personalized federated domain adaptation for item-to-item recommendation

Ziwei Fan, Hao Ding, Anoop Deoras, Trong Nghia Hoang
Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence, PMLR 216:560-570, 2023.

Abstract

Item-to-Item (I2I) recommendation is an important function that suggests replacement or complement options for an item based on their functional similarities or synergies. To capture such item relationships effectively, the recommenders need to understand why subsets of items are co-viewed or co-purchased by the customers. Graph-based models, such as graph neural networks (GNNs), provide a natural framework to combine, ingest and extract valuable insights from such high-order item relationships. However, learning GNNs effectively for I2I requires ingesting a large amount of relational data, which might not always be available, especially in new, emerging market segments. To mitigate this data bottleneck, we postulate that recommendation patterns learned from existing market segments (with private data) could be adapted to build effective warm-start models for emerging ones. To achieve this, we introduce a personalized graph adaptation model based on GNNs to summarize, assemble and adapt recommendation patterns across market segments with heterogeneous customer behaviors into effective local models.

Cite this Paper

BibTeX
@InProceedings{pmlr-v216-fan23a, title = {Personalized federated domain adaptation for item-to-item recommendation}, author = {Fan, Ziwei and Ding, Hao and Deoras, Anoop and Hoang, Trong Nghia}, booktitle = {Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence}, pages = {560--570}, year = {2023}, editor = {Evans, Robin J. and Shpitser, Ilya}, volume = {216}, series = {Proceedings of Machine Learning Research}, month = {31 Jul--04 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v216/fan23a/fan23a.pdf}, url = {https://proceedings.mlr.press/v216/fan23a.html}, abstract = {Item-to-Item (I2I) recommendation is an important function that suggests replacement or complement options for an item based on their functional similarities or synergies. To capture such item relationships effectively, the recommenders need to understand why subsets of items are co-viewed or co-purchased by the customers. Graph-based models, such as graph neural networks (GNNs), provide a natural framework to combine, ingest and extract valuable insights from such high-order item relationships. However, learning GNNs effectively for I2I requires ingesting a large amount of relational data, which might not always be available, especially in new, emerging market segments. To mitigate this data bottleneck, we postulate that recommendation patterns learned from existing market segments (with private data) could be adapted to build effective warm-start models for emerging ones. To achieve this, we introduce a personalized graph adaptation model based on GNNs to summarize, assemble and adapt recommendation patterns across market segments with heterogeneous customer behaviors into effective local models.} }
Endnote
%0 Conference Paper %T Personalized federated domain adaptation for item-to-item recommendation %A Ziwei Fan %A Hao Ding %A Anoop Deoras %A Trong Nghia Hoang %B Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2023 %E Robin J. Evans %E Ilya Shpitser %F pmlr-v216-fan23a %I PMLR %P 560--570 %U https://proceedings.mlr.press/v216/fan23a.html %V 216 %X Item-to-Item (I2I) recommendation is an important function that suggests replacement or complement options for an item based on their functional similarities or synergies. To capture such item relationships effectively, the recommenders need to understand why subsets of items are co-viewed or co-purchased by the customers. Graph-based models, such as graph neural networks (GNNs), provide a natural framework to combine, ingest and extract valuable insights from such high-order item relationships. However, learning GNNs effectively for I2I requires ingesting a large amount of relational data, which might not always be available, especially in new, emerging market segments. To mitigate this data bottleneck, we postulate that recommendation patterns learned from existing market segments (with private data) could be adapted to build effective warm-start models for emerging ones. To achieve this, we introduce a personalized graph adaptation model based on GNNs to summarize, assemble and adapt recommendation patterns across market segments with heterogeneous customer behaviors into effective local models.
APA
Fan, Z., Ding, H., Deoras, A. & Hoang, T.N.. (2023). Personalized federated domain adaptation for item-to-item recommendation. Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 216:560-570 Available from https://proceedings.mlr.press/v216/fan23a.html.

Related Material