Latent variable collaborative filtering methods have been a standard approach to modelling user-click interactions due to their simplicity and effectiveness. However, there is limited work on analyzing the mathematical properties of these methods in particular on preventing the overfitting towards the identity, and such methods typically utilize loss functions that overlook the geometry between items. In this work, we introduce a notion of generalization gap in collaborative filtering and analyze this with respect to latent collaborative filtering models. We present a geometric upper bound that gives rise to loss functions, and a way to meaningfully utilize the geometry of the items to improve recommendations. We show how these losses can be minimized and gives the recipe to a new latent collaborative filtering algorithm, which we refer to as GeoCF, due to the geometric nature of our results. We then show experimentally that our proposed GeoCF algorithm can outperform other all existing methods on the Movielens20M and Netflix datasets, as well as two large-scale internal datasets. In summary, our work proposes a theoretically sound method which paves a way to better understand generalization of collaborative filtering at large.

For many recommender systems, the primary data source is a historical record of user clicks. The associated click matrix is often very sparse, as the number of users × products can be far larger than the number of clicks. Such sparsity is accentuated in cold-start settings, which makes the efficient use of metadata information of paramount importance. In this work, we propose a simple approach to address cold-start recommendations by leveraging content metadata, Metadata Alignment for cold-start Recommendation (MARec). We show that this approach can readily augment existing matrix factorization and autoencoder approaches, enabling a smooth transition to top performing algorithms in warmer set-ups. Our experimental results indicate three separate contributions: first, we show that our proposed framework largely beats SOTA results on 4 cold-start datasets with different sparsity and scale characteristics, with gains ranging from +8.4% to +53.8% on reported ranking metrics; second, we provide an ablation study on the utility of semantic features, and proves the additional gain obtained by leveraging such features ranges between +46.8% and +105.5%; and third, our approach is by construction highly competitive in warm set-ups, and we propose a closed-form solution outperformed by SOTA results by only 0.8% on average.

The transport literature is dense regarding short-term traffic predictions, up to the scale of 1 hour, yet less dense for long-term traffic predictions. The transport literature is also sparse when it comes to city-scale traffic predictions, mainly because of low data availability. In this work, we report an effort to investigate whether deep learning models can be useful for the long-term large-scale traffic prediction task, while focusing on the scalability of the models. We investigate a city-scale traffic dataset with 14 weeks of speed observations collected every 15 minutes over 1098 segments in the hypercenter of Los Angeles, California. We look at a variety of state-of-the-art machine learning and deep learning predictors for link-based predictions, and investigate how such predictors can scale up to larger areas with clustering, and graph convolutional approaches. We discuss that modelling temporal and spatial features into deep learning predictors can be helpful for long-term predictions, while simpler, not deep learning-based predictors, achieve very satisfactory performance for link-based and short-term forecasting. The trade-off is discussed not only in terms of prediction accuracy vs prediction horizon but also in terms of training time and model sizing.

Abstract Human drivers naturally adapt their behaviour depending on the traffic conditions, such as the current weather and road type. Autonomous vehicles need to do the same, in a way that is both safe and efficient in traffic composed of both conventional and autonomous vehicles. In this paper, we demonstrate the applicability of a reconfigurable vehicle controller agent for autonomous vehicles that adapts the parameters of a used car‐following model at runtime, so as to maintain a high degree of traffic quality (efficiency and safety) under different weather conditions. We follow a dynamic software product line approach to model the variability of the car‐following model parameters, context changes and traffic quality, and generate specific configurations for each particular context. Under realistic conditions, autonomous vehicles have only a very local knowledge of other vehicles' variables. We investigate a distributed model predictive controller agent for autonomous vehicles to estimate their behavioural parameters at runtime, based on their available knowledge of the system. We show that autonomous vehicles with the proposed reconfigurable controller agent lead to behaviour similar to that achieved by human drivers, depending on the context.

Stability analyses have been widely used to better understand the mechanism of traffic jam formation. In this paper, we consider the impact of cooperative systems (a.k.a. connected vehicles) on traffic dynamics and, more precisely, on flow stability. Cooperative systems are emerging technologies enabling communication between vehicles and/or with the infrastructure. In a distributed communication framework, equipped vehicles are able to send and receive information to/from other equipped vehicles. Here, the effects of cooperative traffic are modeled through a general bilateral multianticipative car-following law that improves cooperative drivers' perception of their surrounding traffic conditions within a given communication range. Linear stability analyses are performed for a broad class of car-following models. They point out different stability conditions in both multianticipative and nonmultianticipative situations. To better understand what happens in unstable conditions, information on the shock wave structure is studied in the weakly nonlinear regime by the mean of the reductive perturbation method. The shock wave equation is obtained for generic car-following models by deriving the Korteweg de Vries equations. We then derive traffic-state-dependent conditions for the sign of the solitary wave (soliton) amplitude. This analytical result is verified through simulations. Simulation results confirm the validity of the speed estimate. The variation of the soliton amplitude as a function of the communication range is provided. The performed linear and weakly nonlinear analyses help justify the potential benefits of vehicle-integrated communication systems and provide new insights supporting the future implementation of cooperative systems.