Search

Despite many recent advances, state-of-the-art recommender systems still struggle to achieve good performance with sparse datasets. To address the sparsity issue, transfer learning techniques have been investigated for recommender systems, but they tend to impose strict constraints on the content and structure of the data in the source and target domains. For transfer learning methods to work well, there should normally be homogeneity between source and target domains, or a high degree of overlap between the source and target items. In this paper we propose a novel transfer learning framework for mitigating the effects of sparsity and insufficient data. Our method requires neither homogeneity nor overlap between the source and target domains. We describe and evaluate a shared parameter auto-encoder to jointly learn representations of user/item aspects in two domains, applying Maximum Mean Discrepancy (MMD) loss during training to ensure that the source and target representations are similar in the distribution space. The approach is evaluated using a number of benchmark datasets to demonstrate improved recommendation performance when learned representations are used in collaborative filtering. The code used for this work is available on github.com.

Traditional Recommender Systems (RS) use central servers to collect user data, compute user profiles and train global recommendation models. Central computation of RS models has great results in performance because the models are trained using all the available information and the full user profiles. However, centralised RS require users to share their whole interaction history with the central server and in general are not scalable as the number of users and interactions increases. Central RSs also have a central point of attack with respect to user privacy, because all user profiles and interactions are stored centrally. In this work we propose DARES, an distributed recommender system algorithm that uses reinforcement learning and is based on the asynchronous advantage actor-critic model (A3C). DARES is developed combining the approaches of A3C and federated learning (FL) and allows users to keep their data locally on their own devices. The system architecture consists of (i) a local recommendation model trained locally on the user devices using their interaction and (ii) a global recommendation model that is trained on a central server using the model updates that are computed on the user devices. We evaluate the proposed algorithm using well-known datasets and we compare its performance against well-known state of the art algorithms. We show that although being distributed and asynchronous, it can achieve comparable and in many cases better performance than current state-of-the-art algorithms.

Neural network-based recommendation algorithms have become the state-of-the-art in recommender systems and can achieve very high predictive accuracy. However, these models are usually considered as black boxes in terms of their interpretability due to the complex structure of their hidden layers. In this research work, we propose MP4Rec, a recommender system using heterogeneous information networks to provide both accurate and explainable recommendations. MP4Rec uses of user-user and item-item similarity matrices and applies a newly proposed pair-wise objective function to make top-N recommendations which are transparent and explainable. The similarity matrices are created from metapaths constructed with the PathSim algorithm, node embeddings with cosine similarity or their combinations. The proposed pair-wise objective function incorporates an additional soft constraint for pushing more explainable items into the top-N recommendations. We have performed several experiments that show the effectiveness of our model by outperforming the state-of-the-art and providing both accurate and explainable recommendations in three well-known datasets.

Under perfect synchronisation conditions, watermarking schemes employing asymmetric spread-spectrum techniques are suitable for copy-protection of audio signals. This paper proposes to combine the use of a robust psychoacoustic projection for the extraction of a watermark feature vector along with non-linear detection functions optimised with side-information. The new proposed scheme benefits from an increased level of security through the use of asymmetric detectors. We apply this scheme to real audio signals and experimental results show an increased robustness to desynchronisation attacks such as random cropping.