journal article Nov 04, 2024

AdaGIN: Adaptive Graph Interaction Network for Click-Through Rate Prediction

Abstract
The goal of click-through rate (CTR) prediction in recommender systems is to effectively work with input features. However, existing CTR prediction models face three main issues. First, many models use a basic approach for feature combinations, leading to noise and reduced accuracy. Second, there is no consideration for the varying importance of features in different interaction orders, affecting model performance. Third, current model architectures struggle to capture different interaction signals from various semantic spaces, leading to sub-optimal performance. To address these issues, we propose the Adaptive Graph Interaction Network (AdaGIN) with the Graph Neural Networks-based Feature Interaction Module (GFIM), the Multi-semantic Feature Interaction Module (MFIM), and the Negative Feedback-based Search (NFS) algorithm. GFIM explicitly aggregates information between features and assesses their importance, while MFIM captures information from different semantic spaces. NFS uses negative feedback to optimize model complexity. Experimental results show AdaGIN outperforms existing models on large-scale public benchmark datasets.
Topics

No keywords indexed for this article. Browse by subject →

References
72
[1]
Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A framework for self-supervised learning of speech representations. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 33, 12449–12460.
[3]
Jianlong Chang Xinbang Zhang Yiwen Guo Gaofeng Meng Shiming Xiang and Chunhong Pan. 2019. Differentiable architecture search with ensemble gumbel-softmax. arXiv:1905.01786. Retrieved from https://arxiv.org/abs/1905.01786
[13]
Emil J. Gumbel. 1948. Statistical Theory of Extreme Values and Some Practical Applications: A Series of Lectures. Vol. 33. US Government Printing Office.
[15]
Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 30, 1024–1034.
[19]
Multilayer feedforward networks are universal approximators

Kurt Hornik, Maxwell Stinchcombe, Halbert White

Neural Networks 10.1016/0893-6080(89)90020-8
[20]
Huawei. 2021. An Open-Source CTR Prediction Library. Retrieved from https://fuxictr.github.io
[21]
Eric Jang, Shixiang Gu, and Ben Poole. 2017. Categorical reparameterization with gumbel-softmax. Stat 1050 (2017), 5.
[24]
Matt J. Kusner and José M. Hernández-Lobato. 2016. GANS for sequences of discrete elements with the Gumbel-softmax distribution. arXiv:1611.04051. Retrieved from https://arxiv.org/abs/1611.04051
[26]
Youru Li, Xiaobo Guo, Wenfang Lin, Mingjie Zhong, Qunwei Li, Zhongyi Liu, Wenliang Zhong, and Zhenfeng Zhu. 2021a. Learning dynamic user interest sequence in knowledge graphs for click-through rate prediction. IEEE Transactions on Knowledge and Data Engineering 35, 1 (2021), 647–657.
[27]
Yujia Li Daniel Tarlow Marc Brockschmidt and Richard Zemel. 2015. Gated graph sequence neural networks. arXiv:1511.05493. Retrieved from https://arxiv.org/abs/1511.05493
[28]
Yujia Li, Daniel Tarlow, Marc Brockschmidt, and Richard S. Zemel. 2016. Gated graph sequence neural networks. In Proceedings of the 4th International Conference on Learning Representations (ICLR ’16).
[31]
Zekun Li Shu Wu Zeyu Cui and Xiaoyu Zhang. 2021. GraphFM: Graph factorization machines for feature interaction modeling. arXiv:2105.11866. Retrieved from https://arxiv.org/abs/2105.11866v1
[35]
Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Köpf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. Pytorch: An imperative style, high-performance deep learning library. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 32, 8026–8037.
[37]
Lutz Prechelt. 2002. Early stopping-but when? In Neural Networks: Tricks of the Trade. Springer, 55–69.
[42]
Shai Shalev-Shwartz, Ohad Shamir, and Shaked Shammah. 2017. Failures of gradient-based deep learning. In Proceedings of the International Conference on Machine Learning. PMLR, 3067–3075.
[43]
Jiayi Shen, Xiantong Zhen, Marcel Worring, and Ling Shao. 2021. Variational multi-task learning with gumbel-softmax priors. Advances in Neural Information Processing Systems 34 (2021), 21031–21042.
[50]
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 5998–6008.

Showing 50 of 72 references

Metrics
10
Citations
72
References
Details
Published
Nov 04, 2024
Vol/Issue
43(1)
Pages
1-31
License
View
Funding
National Science Foundation of China Award: 62272001 and 62206002
Hefei Key Common Technology Project Award: GJ2022GX15
Cite This Article
Lei Sang, Honghao Li, Yiwen Zhang, et al. (2024). AdaGIN: Adaptive Graph Interaction Network for Click-Through Rate Prediction. ACM Transactions on Information Systems, 43(1), 1-31. https://doi.org/10.1145/3681785
Related

You May Also Like

Evaluating collaborative filtering recommender systems

Jonathan L. Herlocker, Joseph A. Konstan · 2004

4,119 citations

Cumulated gain-based evaluation of IR techniques

Kalervo Järvelin, Jaana Kekäläinen · 2002

3,332 citations

Item-based top-Nrecommendation algorithms

Mukund Deshpande, George Karypis · 2004

1,700 citations

Latent semantic models for collaborative filtering

Thomas Hofmann · 2004

987 citations