Balázs Hidasi

Parallel Recurrent Neural Network Architectures for Feature-rich Session-based Recommendations

Real-life recommender systems often face the daunting task of providing recommendations based only on the clicks of a user session. Methods that rely on user profiles -- such as matrix factorization -- perform very poorly in this setting, thus item-to-item recommendations are used most of the time. However the items typically have rich feature representations such as pictures and text descriptions that can be used to model the sessions. Here we investigate how these features can be exploited in Recurrent Neural Network based session models using deep learning. We show that obvious approaches do not leverage these data sources. We thus introduce a number of parallel RNN (p-RNN) architectures to model sessions based on the clicks and the features (images and text) of the clicked items. We also propose alternative training strategies for p-RNNs that suit them better than standard training. We show that p-RNN architectures with proper training have significant performance improvements over feature-less session models while all session-based models outperform the item-to-item type baseline.

General factorization framework for context-aware recommendations

Context-aware recommendation algorithms focus on refining recommendations by considering additional information, available to the system. This topic has gained a lot of attention recently. Among others, several factorization methods were proposed to solve the problem, although most of them assume explicit feedback which strongly limits their real-world applicability. While these algorithms apply various loss functions and optimization strategies, the preference modeling under context is less explored due to the lack of tools allowing for easy experimentation with various models. As context dimensions are introduced beyond users and items, the space of possible preference models and the importance of proper modeling largely increases. In this paper we propose a general factorization framework (GFF), a single flexible algorithm that takes the preference model as an input and computes latent feature matrices for the input dimensions. GFF allows us to easily experiment with various linear models on any context-aware recommendation task, be it explicit or implicit feedback based. The scaling properties makes it usable under real life circumstances as well. We demonstrate the framework’s potential by exploring various preference models on a 4-dimensional context-aware problem with contexts that are available for almost any real life datasets. We show in our experiments—performed on five real life, implicit feedback datasets—that proper preference modelling significantly increases recommendation accuracy, and previously unused models outperform the traditional ones. Novel models in GFF also outperform state-of-the-art factorization algorithms. We also extend the method to be fully compliant to the Multidimensional Dataspace Model, one of the most extensive data models of context-enriched data. Extended GFF allows the seamless incorporation of information into the factorization framework beyond context, like item metadata, social networks, session information, etc. Preliminary experiments show great potential of this capability.

Personalizing Session-based Recommendations with Hierarchical Recurrent Neural Networks

Session-based recommendations are highly relevant in many modern on-line services (e.g. e-commerce, video streaming) and recommendation settings. Recently, Recurrent Neural Networks have been shown to perform very well in session-based settings. While in many session-based recommendation domains user identifiers are hard to come by, there are also domains in which user profiles are readily available. We propose a seamless way to personalize RNN models with cross-session information transfer and devise a Hierarchical RNN model that relays end evolves latent hidden states of the RNNs across user sessions. Results on two industry datasets show large improvements over the session-only RNNs.

Recurrent Neural Networks with Top-k Gains for Session-based Recommendations

RNNs have been shown to be excellent models for sequential data and in particular for data that is generated by users in an session-based manner. The use of RNNs provides impressive performance benefits over classical methods in session-based recommendations. In this work we introduce novel ranking loss functions tailored to RNNs in the recommendation setting. The improved performance of these losses over alternatives, along with further tricks and refinements described in this work, allow for an overall improvement of up to 35% in terms of MRR and Recall@20 over previous session-based RNN solutions and up to 53% over classical collaborative filtering approaches. Unlike data augmentation-based improvements, our method does not increase training times significantly. We further demonstrate the performance gain of the RNN over baselines in an online A/B test.

Deep Learning for Recommender Systems

Deep Learning is one of the next big things in Recommendation Systems technology. The past few years have seen the tremendous success of deep neural networks in a number of complex machine learning tasks such as computer vision, natural language processing and speech recognition. After its relatively slow uptake by the recommender systems community, deep learning for recommender systems became widely popular in 2016. We believe that a tutorial on the topic of deep learning will do its share to further popularize the topic. Notable recent application areas are music recommendation, news recommendation, and session-based recommendation. The aim of the tutorial is to encourage the application of Deep Learning techniques in Recommender Systems, to further promote research in deep learning methods for Recommender Systems.

Context-aware item-to-item recommendation within the factorization framework

Item-to-item recommendation -- when the most similar items sought to the actual item -- is an important recommendation scenario in practical recommender systems. One way to solve this task is to use the similarity between item feature vectors of factorization models. By doing so, one may transfer the well-known accuracy of factorization models observed at the personalized recommendations to the item-to-item case. This paper introduces context-awareness to item similarities in the factorization framework. Two levels of context-aware similarities are defined and applied to two context-aware implicit feedback based factorization methods (iTALS and iTALSx). We investigate the advantages and drawbacks of the approaches on four real life implicit feedback data sets and we characterize the conditions for their application. The results suggest that it is worth using contextual information for item-to-item recommendations in the factorization framework, however, one should carefully select the appropriate method to achieve similar accuracy gain than in the case of the more general item-to-user recommendation scenario.

ShiftTree: an interpretable model-based approach for time series classification

Efficient algorithms of time series data mining have the common denominator of utilizing the special time structure of the attributes of time series. To accommodate the information of time dimension into the process, we propose a novel instance-level cursor based indexing technique, which is combined with a decision tree algorithm. This is beneficial for several reasons: (a) it is insensitive to the time level noise (for example rendering, time shifting), (b) its working method can be interpreted, making the explanation of the classification process more understandable, and (c) it can manage time series of different length. The implemented algorithm named ShiftTree is compared to the well-known instance-based time series classifier 1-NN using different distance metrics, used over all 20 datasets of a public benchmark time series database and two more public time series datasets. On these benchmark datasets, our experiments show that the new model-based algorithm has an average accuracy slightly better than the most efficient instance-based methods, and there are multiple datasets where our model-based classifier exceeds the accuracy of instance-based methods. We also evaluated our algorithm via blind testing on the 20 datasets of the SIGKDD 2007 Time Series Classification Challenge. To improve the model accuracy and to avoid model overfitting, we provide forest methods as well.

DLRS 2017: Second Workshop on Deep Learning for Recommender Systems

Deep learning methods became widely popular in the recommender systems community in 2016, in part thanks to the previous event of the DLRS workshop series. Now, deep learning has been embedded in the main conference as well and initial research directions have started forming, so the role of DLRS 2017 is to encourage starting new research directions, incentivize the application of very recent techniques from deep learning, and provide a venue for specialized discussion of this topic.

RecSys'16 Workshop on Deep Learning for Recommender Systems (DLRS)

We believe that Deep Learning is one of the next big things in Recommendation Systems technology. The past few years have seen the tremendous success of deep neural networks in a number of complex tasks such as computer vision, natural language processing and speech recognition. Despite this, only little work has been published on Deep Learning methods for Recommender Systems. Notable recent application areas are music recommendation, news recommendation, and session-based recommendation. The aim of the workshop is to encourage the application of Deep Learning techniques in Recommender Systems, to promote research in deep learning methods for Recommender Systems, and to bring together researchers from the Recommender Systems and Deep Learning communities.

Approximate modeling of continuous context in factorization algorithms

Factorization based algorithms -- such as matrix or tensor factorization -- are widely used in the field of recommender systems. These methods model the relations between the entities of two or more dimensions. The entity based approach is suitable for dimensions such as users, items and several context types, where the domain of the context is nominal. Continuous and ordinal context dimensions are usually discretized and their values are used as nominal entities. While this enables the usage of continuous context in factorization methods, still much information is lost during the process. In this paper we propose two approaches for better modeling of the continuous context dimensions. Fuzzy event modeling tackles the problem through the uncertainty of the value of the observation in the context dimension. Fuzzy context modeling, on the other hand, enables context-states to overlap, thus certain observations are influenced by multiple context-states. Throughout the paper seasonality is used as an example of continuous context. We incorporate the modeling concepts into the iTALS algorithm, without degrading its scalability. The effect of the two approaches on recommendation accuracy is measured on five implicit feedback databases.