Building robust online content recommendation systems requires learning complex interactions between user preferences and content features. The field has evolved rapidly in recent years from traditional multi-arm bandit and collaborative filtering techniques, with new methods employing Deep Learning models to capture non-linearities. Despite progress, the dynamic nature of online recommendations still poses great challenges, such as finding the delicate balance between exploration and exploitation. In this paper we show how uncertainty estimations can be incorporated by employing them in an optimistic exploitation/exploration strategy for more efficient exploration of new recommendations. We provide a novel hybrid deep neural network model, Deep Density Networks (DDN), which integrates content-based deep learning models with a collaborative scheme that is able to robustly model and estimate uncertainty. Finally, we present online and offline results after incorporating DNN into a real world content recommendation system that serves billions of recommendations per day, and show the benefit of using DDN in practice.
Two-sided marketplaces are an important component of many existing Internet services like Airbnb and Amazon, which have both consumers (e.g. users) and producers (e.g. retailers). Traditionally, the recommendation system in these platforms mainly focuses on maximizing customer satisfaction by recommending the most relevant items based on the learned user preference. However, it has been shown in previous works that solely optimizing the satisfaction of customers may lead to unfair exposure of items, which jeopardizes the benefits of producers. To tackle this problem, we propose a fairness-aware recommendation framework by using multi-objective optimization, Multi-FR, to adaptively balance the objectives between consumers and producers. In particular, Multi-FR adopts the multi-gradient descent to generate a Pareto set of solutions, where the most appropriate one is selected from the Pareto set. In addition, four fairness metrics/constraints are applied to make the recommendation results on both the consumer and producer side fair. We extensively evaluate our model on three real-world datasets, comparing with grid-search methods and using a variety of performance metrics. The experimental results demonstrate that Multi-FR can improve the recommendation fairness on both the consumer and producer side with little drop in recommendation quality, also outperforming several state-of-the-art fair ranking approaches.
Social activities play an important role in people's daily life since they interact. For recommendations based on social activities, it is vital to have not only the activity information but also individuals' social relations. Thanks to the geo-social networks and widespread use of location-aware mobile devices, massive geo-social data is now readily available for exploitation by the recommendation system. In this paper, a novel group recommendation method, called attentive geo-social group recommendation, is proposed to recommend the target user with both activity locations and a group of users that may join the activities. We present an attention mechanism to model the influence of the target user $u_T$ in candidate user groups that satisfy the social constraints. It helps to retrieve the optimal user group and activity topic candidates, as well as explains the group decision-making process. Once the user group and topics are retrieved, a novel efficient spatial query algorithm SPA-DF is employed to determine the activity location under the constraints of the given user group and activity topic candidates. The proposed method is evaluated in real-world datasets and the experimental results show that the proposed model significantly outperforms baseline methods.
Session based recommendation provides an attractive alternative to the traditional feature engineering approach to recommendation. Feature engineering approaches require hand tuned features of the users history to be created to produce a context vector. In contrast a session based approach is able to dynamically model the users state as they act. We present a probabilistic framework for session based recommendation. A latent variable for the user state is updated as the user views more items and we learn more about their interests. The latent variable model is conceptually simple and elegant; yet requires sophisticated computational technique to approximate the integral over the latent variable. We provide computational solutions using both the re-parameterization trick and also using the Bouchard bound for the softmax function, we further explore employing a variational auto-encoder and a variational Expectation-Maximization algorithm for tightening the variational bound. The model performs well against a number of baselines. The intuitive nature of the model allows an elegant formulation combining correlations between items and their popularity and that sheds light on other popular recommendation methods. An attractive feature of the latent variable approach is that, as the user continues to act, the posterior on the users state tightens reflecting the recommender system's increased knowledge about that user.
Social relations are often used to improve recommendation quality when user-item interaction data is sparse in recommender systems. Most existing social recommendation models exploit pairwise relations to mine potential user preferences. However, real-life interactions among users are very complicated and user relations can be high-order. Hypergraph provides a natural way to model complex high-order relations, while its potentials for improving social recommendation are under-explored. In this paper, we fill this gap and propose a multi-channel hypergraph convolutional network to enhance social recommendation by leveraging high-order user relations. Technically, each channel in the network encodes a hypergraph that depicts a common high-order user relation pattern via hypergraph convolution. By aggregating the embeddings learned through multiple channels, we obtain comprehensive user representations to generate recommendation results. However, the aggregation operation might also obscure the inherent characteristics of different types of high-order connectivity information. To compensate for the aggregating loss, we innovatively integrate self-supervised learning into the training of the hypergraph convolutional network to regain the connectivity information with hierarchical mutual information maximization. The experimental results on multiple real-world datasets show that the proposed model outperforms the SOTA methods, and the ablation study verifies the effectiveness of the multi-channel setting and the self-supervised task. The implementation of our model is available via https://github.com/Coder-Yu/RecQ.
As a crucial component of most modern deep recommender systems, feature embedding maps high-dimensional sparse user/item features into low-dimensional dense embeddings. However, these embeddings are usually assigned a unified dimension, which suffers from the following issues: (1) high memory usage and computation cost. (2) sub-optimal performance due to inferior dimension assignments. In order to alleviate the above issues, some works focus on automated embedding dimension search by formulating it as hyper-parameter optimization or embedding pruning problems. However, they either require well-designed search space for hyperparameters or need time-consuming optimization procedures. In this paper, we propose a Single-Shot Embedding Dimension Search method, called SSEDS, which can efficiently assign dimensions for each feature field via a single-shot embedding pruning operation while maintaining the recommendation accuracy of the model. Specifically, it introduces a criterion for identifying the importance of each embedding dimension for each feature field. As a result, SSEDS could automatically obtain mixed-dimensional embeddings by explicitly reducing redundant embedding dimensions based on the corresponding dimension importance ranking and the predefined parameter budget. Furthermore, the proposed SSEDS is model-agnostic, meaning that it could be integrated into different base recommendation models. The extensive offline experiments are conducted on two widely used public datasets for CTR prediction tasks, and the results demonstrate that SSEDS can still achieve strong recommendation performance even if it has reduced 90\% parameters. Moreover, SSEDS has also been deployed on the WeChat Subscription platform for practical recommendation services. The 7-day online A/B test results show that SSEDS can significantly improve the performance of the online recommendation model.
Herb recommendation plays a crucial role in the therapeutic process of Traditional Chinese Medicine(TCM), which aims to recommend a set of herbs to treat the symptoms of a patient. While several machine learning methods have been developed for herb recommendation, they are limited in modeling only the interactions between herbs and symptoms, and ignoring the intermediate process of syndrome induction. When performing TCM diagnostics, an experienced doctor typically induces syndromes from the patient's symptoms and then suggests herbs based on the induced syndromes. As such, we believe the induction of syndromes, an overall description of the symptoms, is important for herb recommendation and should be properly handled. However, due to the ambiguity and complexity of syndrome induction, most prescriptions lack the explicit ground truth of syndromes. In this paper, we propose a new method that takes the implicit syndrome induction process into account for herb recommendation. Given a set of symptoms to treat, we aim to generate an overall syndrome representation by effectively fusing the embeddings of all the symptoms in the set, to mimic how a doctor induces the syndromes. Towards symptom embedding learning, we additionally construct a symptom-symptom graph from the input prescriptions for capturing the relations between symptoms; we then build graph convolution networks(GCNs) on both symptom-symptom and symptom-herb graphs to learn symptom embedding. Similarly, we construct a herb-herb graph and build GCNs on both herb-herb and symptom-herb graphs to learn herb embedding, which is finally interacted with the syndrome representation to predict the scores of herbs. In this way, more comprehensive representations can be obtained. We conduct extensive experiments on a public TCM dataset, showing significant improvements over state-of-the-art herb recommendation methods.
We present a large scale hyperbolic recommender system. We discuss why hyperbolic geometry is a more suitable underlying geometry for many recommendation systems and cover the fundamental milestones and insights that we have gained from its development. In doing so, we demonstrate the viability of hyperbolic geometry for recommender systems, showing that they significantly outperform Euclidean models on datasets with the properties of complex networks. Key to the success of our approach are the novel choice of underlying hyperbolic model and the use of the Einstein midpoint to define an asymmetric recommender system in hyperbolic space. These choices allow us to scale to millions of users and hundreds of thousands of items.