Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Decentralized Collaborative Learning with Adaptive Reference Data for On-Device POI Recommendation (2401.13448v2)

Published 24 Jan 2024 in cs.IR

Abstract: In Location-based Social Networks, Point-of-Interest (POI) recommendation helps users discover interesting places. There is a trend to move from the cloud-based model to on-device recommendations for privacy protection and reduced server reliance. Due to the scarcity of local user-item interactions on individual devices, solely relying on local instances is not adequate. Collaborative Learning (CL) emerges to promote model sharing among users, where reference data is an intermediary that allows users to exchange their soft decisions without directly sharing their private data or parameters, ensuring privacy and benefiting from collaboration. However, existing CL-based recommendations typically use a single reference for all users. Reference data valuable for one user might be harmful to another, given diverse user preferences. Users may not offer meaningful soft decisions on items outside their interest scope. Consequently, using the same reference data for all collaborations can impede knowledge exchange and lead to sub-optimal performance. To address this gap, we introduce the Decentralized Collaborative Learning with Adaptive Reference Data (DARD) framework, which crafts adaptive reference data for effective user collaboration. It first generates a desensitized public reference data pool with transformation and probability data generation methods. For each user, the selection of adaptive reference data is executed in parallel by training loss tracking and influence function. Local models are trained with individual private data and collaboratively with the geographical and semantic neighbors. During the collaboration between two users, they exchange soft decisions based on a combined set of their adaptive reference data. Our evaluations across two real-world datasets highlight DARD's superiority in recommendation performance and addressing the scarcity of available reference data.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (48)
  1. Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation. Computer Science (2013).
  2. Distributed Distillation for On-Device Learning. In Neural Information Processing Systems.
  3. Content-Aware Hierarchical Point-of-Interest Embedding Model for Successive POI Recommendation. In Twenty-Seventh International Joint Conference on Artificial Intelligence IJCAI-18.
  4. Privacy preserving point-of-interest recommendation using decentralized matrix factorization. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32.
  5. Compressing Neural Networks with the Hashing Trick.
  6. Will You Come Back / Check-in Again? Understanding Characteristics Leading to Urban Revisitation and Re-check-in. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies (2020).
  7. Deep learning. MIT press.
  8. PREFER: Point-of-interest REcommendation with efficiency and privacy-preservation via Federated Edge leaRning. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies 5, 1 (2021), 1–25.
  9. Distilling the Knowledge in a Neural Network. Computer Science 14, 7 (2015), 38–39.
  10. S. Hochreiter and J. Schmidhuber. 1997. Long Short-Term Memory. Neural Computation 9, 8 (1997), 1735–1780.
  11. Peter J Huber. 2004. Robust statistics. Vol. 523. John Wiley & Sons.
  12. Pang Wei Koh and Percy Liang. 2017. Understanding black-box predictions via influence functions. In International conference on machine learning. PMLR, 1885–1894.
  13. On the accuracy of influence functions for measuring group effects. Advances in neural information processing systems 32 (2019).
  14. Resolving training biases via influence-based data relabeling. In International Conference on Learning Representations.
  15. Matrix factorization techniques for recommender systems. Computer 42, 8 (2009), 30–37.
  16. W. Krichene and S. Rendle. 2020. On Sampled Metrics for Item Recommendation. In KDD ’20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.
  17. Next Point-of-Interest Recommendation with Temporal and Multi-level Context Attention. 2018 IEEE International Conference on Data Mining (ICDM) (2018), 1110–1115.
  18. Discovering Collaborative Signals for Next POI Recommendation with Iterative Seq2Graph Augmentation.
  19. Geography-Aware Sequential Location Recommendation. In KDD ’20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.
  20. GeoMF: joint geographical modeling and matrix factorization for point-of-interest recommendation. ACM.
  21. Fedrec++: Lossless federated recommendation with explicit feedback. In Proceedings of the AAAI conference on artificial intelligence, Vol. 35. 4224–4231.
  22. Personalized point-of-interest recommendation by mining users’ preference transition. In Acm International Conference on Conference on Information & Knowledge Management.
  23. Decentralized Collaborative Learning Framework for Next POI Recommendation. TOIS (2022).
  24. Model-Agnostic Decentralized Collaborative Learning for On-Device POI Recommendation. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. 423–432.
  25. STAN: Spatio-Temporal Attention Network for Next Location Recommendation.
  26. J. Macqueen. 1967. Some methods for classification and analysis of multivariate observations. Proc. Symp. Math. Statist. and Probability, 5th 1 (1967).
  27. A survey of matrix completion methods for recommendation systems. Big Data Mining and Analytics 1, 4 (2018), 308–323.
  28. Robust and communication-efficient collaborative learning. Advances in Neural Information Processing Systems 32 (2019).
  29. S. Rendle. 2012. Factorization Machines with libFM. ACM Transactions on Intelligent Systems and Technology 3, 3 (2012), 1–22.
  30. Decentralized collaborative learning of personalized models over networks. In Artificial Intelligence and Statistics. PMLR, 509–517.
  31. Next Point-of-Interest Recommendation on Resource-Constrained Mobile Devices. In WWW ’20: The Web Conference 2020.
  32. Fast-adapting and privacy-preserving federated recommender system. The VLDB Journal 31, 5 (2022), 877–896.
  33. Neural Memory Streaming Recommender Networks with Adversarial Training. (2018), 2467–2475.
  34. Enhancing Collaborative Filtering with Generative Augmentation. In the 25th ACM SIGKDD International Conference.
  35. Less is better: Unweighted data subsampling via influence function. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 6340–6347.
  36. CoFiRank - Maximum Margin Matrix Factorization for Collaborative Ranking. In Neural Information Processing Systems.
  37. Efficient on-device session-based recommendation. ACM Transactions on Information Systems 41, 4 (2023), 1–24.
  38. A Decentralized Collaborative Learning Framework Across Heterogeneous Devices for Personalized Predictive Analytics. (2022).
  39. Joint modeling of users’ interests and mobility patterns for point-of-interest recommendation. In Proceedings of the 23rd ACM international conference on Multimedia. 819–822.
  40. On-Device Recommender Systems: A Comprehensive Survey. arXiv:2401.11441 [cs.IR]
  41. Spatial-aware hierarchical collaborative deep learning for POI recommendation. IEEE Transactions on Knowledge and Data Engineering 29, 11 (2017), 2537–2551.
  42. Influence function for unbiased recommendation. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 1929–1932.
  43. HeteFedRec: Federated Recommender Systems with Model Heterogeneity. arXiv preprint arXiv:2307.12810 (2023).
  44. Interaction-level membership inference attack against federated recommender systems. arXiv preprint arXiv:2301.10964 (2023).
  45. Graph embedding for recommendation against attribute inference attacks. In Proceedings of the Web Conference 2021. 3002–3014.
  46. Comprehensive privacy analysis on federated recommender system against attribute inference attacks. IEEE Transactions on Knowledge and Data Engineering (2023).
  47. Zhi-Dan Zhao and Ming-Sheng Shang. 2010. User-based collaborative-filtering recommendation algorithms on hadoop. In 2010 third international conference on knowledge discovery and data mining. IEEE, 478–481.
  48. Personalized Elastic Embedding Learning for On-Device Recommendation. arXiv preprint arXiv:2306.10532 (2023).
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Ruiqi Zheng (11 papers)
  2. Liang Qu (22 papers)
  3. Tong Chen (201 papers)
  4. Lizhen Cui (66 papers)
  5. Yuhui Shi (44 papers)
  6. Hongzhi Yin (211 papers)
Citations (7)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now