Now showing 1 - 4 of 4
  • Publication
    FedFast: Going Beyond Average for Faster Training of Federated Recommender Systems
    Federated learning (FL) is quickly becoming the de facto standard for the distributed training of deep recommendation models, us-ing on-device user data and reducing server costs. In a typical FLprocess, a central server tasks end-users to train a shared recommen-dation model using their local data. The local models are trained over several rounds on the users’ devices and the server combinesthem into a global model, which is sent to the devices for the pur-pose of providing recommendations. Standard FL approaches userandomly selected users for training at each round, and simply average their local models to compute the global model. The resulting federated recommendation models require significant client effortto train and many communication rounds before they converge to asatisfactory accuracy. Users are left with poor quality recommendations until the late stages of training. We present a novel technique, FedFast, to accelerate distributed learning which achieves goodaccuracy for all users very early in the training process. We achievethis by sampling from a diverse set of participating clients in each training round and applying an active aggregation method that propagates the updated model to the other clients. Consequently, with FedFast the users benefit from far lower communication costsand more accurate models that can be consumed anytime during the training process even at the very early stages. We demonstrate the efficacy of our approach across a variety of benchmark datasetsand in comparison to state-of-the-art recommendation techniques
    Scopus© Citations 106  563
  • Publication
    PDMFRec: A Decentralised Matrix Factorisation with Tunable User-centric Privacy
    Conventional approaches to matrix factorisation (MF) typically rely on a centralised collection of user data for building a MF model. This approach introduces an increased risk when it comes to user privacy. In this short paper we propose an alternative, user-centric, privacy enhanced, decentralised approach to MF. Our method pushes the computation of the recommendation model to the user’s device, and eliminates the need to exchange sensitive personal information; instead only the loss gradients of local (device-based) MF models need to be shared. Moreover, users can select the amount and type of information to be shared, for enhanced privacy. We demonstrate the effectiveness of this approach by considering different levels of user privacy in comparison with state-of-the-art alternatives.
    Scopus© Citations 26  482
  • Publication
    Combining Rating and Review Data by Initializing Latent Factor Models with Topic Models for Top-N Recommendation
    Nowadays we commonly have multiple sources of data associated with items. Users may provide numerical ratings, or implicit interactions, but may also provide textual reviews. Although many algorithms have been proposed to jointly learn a model over both interactions and textual data, there is room to improve the many factorization models that are proven to work well on interactions data, but are not designed to exploit textual information. Our focus in this work is to propose a simple, yet easily applicable and effective, method to incorporate review data into such factorization models. In particular, we propose to build the user and item embeddings within the topic space of a topic model learned from the review data. This has several advantages: we observe that initializing the user and item embeddings in topic space leads to faster convergence of the factorization algorithm to a model that out-performs models initialized randomly, or with other state-of-the-art initialization strategies. Moreover, constraining user and item factors to topic space allows for the learning of an interpretable model that users can visualise.
    Scopus© Citations 19  59
  • Publication
    A Distributed Asynchronous Deep Reinforcement Learning Framework for Recommender Systems
    In this paper we propose DADRL, a distributed, asynchronous reinforcement learning recommender system based on the asynchronous advantage actor-critic model (A3C), which combines ideas from A3C and federated learning (FL). The proposed algorithm keeps the user preferences or interactions on local devices and uses a combination of on-device, local recommendation models and a complementary global model. The global model is trained only by the loss gradients of the local models, rather than directly using user preferences or interactions data. We demonstrate, using well-known datasets and benchmark algorithms, how this approach can deliver performance that is comparable with the current state-of-the-art while enhancing user privacy.
      452