Published on Mon Jul 24 2017

Share your Model instead of your Data: Privacy Preserving Mimic Learning for Ranking

Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, Maarten de Rijke

Deep neural networks have become a primary tool for solving problems in many fields. Training these models requires large,representative datasets. For most IR tasks, such data contains sensitive information from users. Privacy and confidentiality concerns prevent many data owners from sharing the data.

0
0
0
Abstract

Deep neural networks have become a primary tool for solving problems in many fields. They are also used for addressing information retrieval problems and show strong performance in several tasks. Training these models requires large, representative datasets and for most IR tasks, such data contains sensitive information from users. Privacy and confidentiality concerns prevent many data owners from sharing the data, thus today the research community can only benefit from research on large-scale datasets in a limited manner. In this paper, we discuss privacy preserving mimic learning, i.e., using predictions from a privacy preserving trained model instead of labels from the original sensitive training data as a supervision signal. We present the results of preliminary experiments in which we apply the idea of mimic learning and privacy preserving mimic learning for the task of document re-ranking as one of the core IR tasks. This research is a step toward laying the ground for enabling researchers from data-rich environments to share knowledge learned from actual users' data, which should facilitate research collaborations.

Wed Aug 18 2021
Machine Learning
Learning Federated Representations and Recommendations with Limited Negatives
Deep retrieval models are widely used for learning entity representations andrecommendations. Federated learning provides a privacy-preserving way to train these models without requiring centralization of user data. However, federated deep retrieval models usually perform much worse than their centralized counterparts.
1
0
0
Sun Aug 12 2018
Machine Learning
Adversarial Personalized Ranking for Recommendation
Adversarial Personalized Ranking (APR) enhances the pairwise ranking method BPR by performing adversarial training. APR can be interpreted as playing a minimax game, where the minimization of the BPR objective function defends an adversary, which adds adversarial perturbations on model parameters. APR is available on GitHub.
0
0
0
Tue Mar 17 2020
Machine Learning
Overview of the TREC 2019 deep learning track
0
0
0
Mon Mar 01 2021
Machine Learning
Wide Network Learning with Differential Privacy
The current generation of neural networks suffers a significant loss of accuracy under most practically relevant privacy training regimes. We demonstrate that for non-convex ERM problems, the loss is logarithmically dependent on the number of parameters. We propose a novel algorithm for privately training neural networks.
0
0
0
Fri Apr 28 2017
Machine Learning
Neural Ranking Models with Weak Supervision
This paper proposes to train a neural ranking model using weak supervision. The output of an unsupervised ranking model, such as BM25, is used as a weak supervision signal. We train a set of simple yet effective ranking models based on feed-forward neural networks.
0
0
0
Tue May 11 2021
Machine Learning
Federated Unbiased Learning to Rank
Unbiased Learning to Rank (ULTR) studies the problem of learning a ranking function based on biased user interactions. ULTR algorithms rely on a large amount of user data that are collected, stored, andaggregated by central servers.
1
0
0