Phase-Adaptive Federated Learning for Privacy-Preserving Personalized Travel Itinerary Generation
We propose Phase-Adaptive Federated Learning (PAFL), a novel framework for privacy-preserving personalized travel itinerary generation that dynamically balances privacy and utility through a phase-dependent aggregation mechanism inspired by phase-change materials. (1) PAFL’s primary objective is to...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Tourism and Hospitality |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-5768/6/2/100 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849425119471992832 |
|---|---|
| author | Xiaolong Chen Hongfeng Zhang Cora Un In Wong |
| author_facet | Xiaolong Chen Hongfeng Zhang Cora Un In Wong |
| author_sort | Xiaolong Chen |
| collection | DOAJ |
| description | We propose Phase-Adaptive Federated Learning (PAFL), a novel framework for privacy-preserving personalized travel itinerary generation that dynamically balances privacy and utility through a phase-dependent aggregation mechanism inspired by phase-change materials. (1) PAFL’s primary objective is to dynamically optimize the privacy–utility trade-off in federated travel recommendation systems through phase-adaptive anonymization. The phase parameter φ ∈ [0, 1] operates as a tunable control variable that continuously adjusts the latent space geometry between differentially private (φ→1) and utility-optimized (φ→0) representations via a thermodynamic-inspired transformation. Conventional federated learning approaches often rely on static privacy-preserving techniques, which either degrade recommendation quality or inadequately protect sensitive user data; PAFL addresses this limitation through three key innovations: a latent-space phase transformer, a differential privacy-gradient inverter with mathematically provable reconstruction bounds (εt ≤ 1.0), and a lightweight sequential transformer. (2) PAFL’s core innovation lies in its phase-adaptive mechanism that dynamically balances privacy preservation through differential privacy and utility maintenance via gradient inversion, governed by the tunable phase parameter φ. Experimental results demonstrate statistically significant improvements, with 18.7% higher HR@10 (<i>p</i> < 0.01) and 62% lower membership inference risk compared to state-of-the-art methods, while maintaining εtotal < 2.3 over 100 training rounds. The framework advances federated learning for sensitive recommendation tasks by establishing a new paradigm for adaptive privacy–utility optimization. |
| format | Article |
| id | doaj-art-c0f0e60258dc405abc46ecc2e9a4b824 |
| institution | Kabale University |
| issn | 2673-5768 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Tourism and Hospitality |
| spelling | doaj-art-c0f0e60258dc405abc46ecc2e9a4b8242025-08-20T03:29:52ZengMDPI AGTourism and Hospitality2673-57682025-06-016210010.3390/tourhosp6020100Phase-Adaptive Federated Learning for Privacy-Preserving Personalized Travel Itinerary GenerationXiaolong Chen0Hongfeng Zhang1Cora Un In Wong2Faculty of Humanities and Social Sciences, Macao Polytechnic University, Macao 999078, ChinaFaculty of Humanities and Social Sciences, Macao Polytechnic University, Macao 999078, ChinaFaculty of Humanities and Social Sciences, Macao Polytechnic University, Macao 999078, ChinaWe propose Phase-Adaptive Federated Learning (PAFL), a novel framework for privacy-preserving personalized travel itinerary generation that dynamically balances privacy and utility through a phase-dependent aggregation mechanism inspired by phase-change materials. (1) PAFL’s primary objective is to dynamically optimize the privacy–utility trade-off in federated travel recommendation systems through phase-adaptive anonymization. The phase parameter φ ∈ [0, 1] operates as a tunable control variable that continuously adjusts the latent space geometry between differentially private (φ→1) and utility-optimized (φ→0) representations via a thermodynamic-inspired transformation. Conventional federated learning approaches often rely on static privacy-preserving techniques, which either degrade recommendation quality or inadequately protect sensitive user data; PAFL addresses this limitation through three key innovations: a latent-space phase transformer, a differential privacy-gradient inverter with mathematically provable reconstruction bounds (εt ≤ 1.0), and a lightweight sequential transformer. (2) PAFL’s core innovation lies in its phase-adaptive mechanism that dynamically balances privacy preservation through differential privacy and utility maintenance via gradient inversion, governed by the tunable phase parameter φ. Experimental results demonstrate statistically significant improvements, with 18.7% higher HR@10 (<i>p</i> < 0.01) and 62% lower membership inference risk compared to state-of-the-art methods, while maintaining εtotal < 2.3 over 100 training rounds. The framework advances federated learning for sensitive recommendation tasks by establishing a new paradigm for adaptive privacy–utility optimization.https://www.mdpi.com/2673-5768/6/2/100travel recommendationfederated learningpersonalized travel itinerary generationprivacy preservingphase-adaptive federated learning |
| spellingShingle | Xiaolong Chen Hongfeng Zhang Cora Un In Wong Phase-Adaptive Federated Learning for Privacy-Preserving Personalized Travel Itinerary Generation Tourism and Hospitality travel recommendation federated learning personalized travel itinerary generation privacy preserving phase-adaptive federated learning |
| title | Phase-Adaptive Federated Learning for Privacy-Preserving Personalized Travel Itinerary Generation |
| title_full | Phase-Adaptive Federated Learning for Privacy-Preserving Personalized Travel Itinerary Generation |
| title_fullStr | Phase-Adaptive Federated Learning for Privacy-Preserving Personalized Travel Itinerary Generation |
| title_full_unstemmed | Phase-Adaptive Federated Learning for Privacy-Preserving Personalized Travel Itinerary Generation |
| title_short | Phase-Adaptive Federated Learning for Privacy-Preserving Personalized Travel Itinerary Generation |
| title_sort | phase adaptive federated learning for privacy preserving personalized travel itinerary generation |
| topic | travel recommendation federated learning personalized travel itinerary generation privacy preserving phase-adaptive federated learning |
| url | https://www.mdpi.com/2673-5768/6/2/100 |
| work_keys_str_mv | AT xiaolongchen phaseadaptivefederatedlearningforprivacypreservingpersonalizedtravelitinerarygeneration AT hongfengzhang phaseadaptivefederatedlearningforprivacypreservingpersonalizedtravelitinerarygeneration AT corauninwong phaseadaptivefederatedlearningforprivacypreservingpersonalizedtravelitinerarygeneration |