Tile Networks: Learning Optimal Geometric Layout for Whole-page Recommendation

Shuai Xiao, Zaifan Jiang, Shuang Yang
Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, PMLR 151:8360-8369, 2022.

Abstract

Finding optimal configurations in a geometric space is a key challenge in many technological disciplines. Current approaches either rely heavily on human domain expertise and are difficult to scale. In this paper we show it is possible to solve configuration optimization problems for whole-page recommendation using reinforcement learning. The proposed Tile Networks is a neural architecture that optimizes 2D geometric configurations by arranging items on proper positions. Empirical results on real dataset demonstrate its superior performance compared to traditional learning to rank approaches and recent deep models.

Cite this Paper

BibTeX
@InProceedings{pmlr-v151-xiao22a, title = { Tile Networks: Learning Optimal Geometric Layout for Whole-page Recommendation }, author = {Xiao, Shuai and Jiang, Zaifan and Yang, Shuang}, booktitle = {Proceedings of The 25th International Conference on Artificial Intelligence and Statistics}, pages = {8360--8369}, year = {2022}, editor = {Camps-Valls, Gustau and Ruiz, Francisco J. R. and Valera, Isabel}, volume = {151}, series = {Proceedings of Machine Learning Research}, month = {28--30 Mar}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v151/xiao22a/xiao22a.pdf}, url = {https://proceedings.mlr.press/v151/xiao22a.html}, abstract = { Finding optimal configurations in a geometric space is a key challenge in many technological disciplines. Current approaches either rely heavily on human domain expertise and are difficult to scale. In this paper we show it is possible to solve configuration optimization problems for whole-page recommendation using reinforcement learning. The proposed Tile Networks is a neural architecture that optimizes 2D geometric configurations by arranging items on proper positions. Empirical results on real dataset demonstrate its superior performance compared to traditional learning to rank approaches and recent deep models. } }
Endnote
%0 Conference Paper %T Tile Networks: Learning Optimal Geometric Layout for Whole-page Recommendation %A Shuai Xiao %A Zaifan Jiang %A Shuang Yang %B Proceedings of The 25th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2022 %E Gustau Camps-Valls %E Francisco J. R. Ruiz %E Isabel Valera %F pmlr-v151-xiao22a %I PMLR %P 8360--8369 %U https://proceedings.mlr.press/v151/xiao22a.html %V 151 %X Finding optimal configurations in a geometric space is a key challenge in many technological disciplines. Current approaches either rely heavily on human domain expertise and are difficult to scale. In this paper we show it is possible to solve configuration optimization problems for whole-page recommendation using reinforcement learning. The proposed Tile Networks is a neural architecture that optimizes 2D geometric configurations by arranging items on proper positions. Empirical results on real dataset demonstrate its superior performance compared to traditional learning to rank approaches and recent deep models.
APA
Xiao, S., Jiang, Z. & Yang, S.. (2022). Tile Networks: Learning Optimal Geometric Layout for Whole-page Recommendation . Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 151:8360-8369 Available from https://proceedings.mlr.press/v151/xiao22a.html.

Related Material