Collaborating Authors

Time-Dependent Simple Temporal Networks: Properties and Algorithms

AAAI Conferences

Simple Temporal Networks (STNs) allow minimum and maximum distance constraints between time-points to be represented. They are often used when tackling planning and scheduling problems that involve temporal aspects. This paper is a summary of the journal article "Time-dependent Simple Temporal Networks: Properties and Algorithms" published in RAIRO - Operations Research. This journal article introduces an extension of STN called Time-dependent STN (TSTN), which covers temporal constraints for which the temporal distance required between two time-points is not necessarily constant. Such constraints are useful to model time-dependent scheduling problems, in which the duration of an activity may depend on its starting time. The paper introduces the TSTN framework, its properties, resolution techniques, as well as examples of applications.

TiDeH: Time-Dependent Hawkes Process for Predicting Retweet Dynamics

AAAI Conferences

Online social networking services allow their users to post content in the form of text, images or videos. The main mechanism driving content diffusion is the possibility for users to re-share the content posted by their social connections, which may then cascade across the system. A fundamental problem when studying information cascades is the possibility to develop sound mathematical models, whose parameters can be calibrated on empirical data, in order to predict the future course of a cascade after a window of observation. In this paper, we focus on Twitter and, in particular, on the temporal patterns of retweet activity for an original tweet. We model the system by Time-Dependent Hawkes process (TiDeH), which properly takes into account the circadian nature of the users and the aging of information. The input of the prediction model are observed retweet times and structural information about the underlying social network. We develop a procedure for parameter optimization and for predicting the future profiles of retweet activity at different time resolutions. We validate our methodology on a large corpus of Twitter data and demonstrate its systematic improvement over existing approaches in all the time regimes.

Time-Dependent Utility and Action Under Uncertainty Artificial Intelligence

We discuss representing and reasoning with knowledge about the time-dependent utility of an agent's actions. Time-dependent utility plays a crucial role in the interaction between computation and action under bounded resources. We present a semantics for time-dependent utility and describe the use of time-dependent information in decision contexts. We illustrate our discussion with examples of time-pressured reasoning in Protos, a system constructed to explore the ideal control of inference by reasoners with limit abilities.

Smart Learning: Time-Dependent Context-Aware Learning Object Recommendations

AAAI Conferences

In a digital classroom, analysis of students' interactions with the learning media provides important information about users' behavior, which can lead to a better understanding and thus optimizes teaching and learning. However, over the period of a course, students tend to forget the lessons learned in class. Learning predictions can be used to recommend learning objects users need most, as well as to give an overview of current knowledge and the learning level. The representation of time based data in such a format is difficult since the knowledge level of a user with a learning object changes continuously depending on various factors. This paper presents work in progress for a doctoral approach to extend the traditional user-item-matrix of a recommendation engine by a third dimension - the time value. Moreover, in this approach the learning need consists of different context factors each influencing the relevance score of a learning object.

Time-Dependent Trajectory Regression on Road Networks via Multi-Task Learning

AAAI Conferences

Road travel costs are important knowledge hidden in large-scale GPS trajectory data sets, the discovery of which can benefit many applications such as intelligent route planning and automatic driving navigation. While there are previous studies which tackled this task by modeling it as a regression problem with spatial smoothness taken into account, they unreasonably assumed that the latent cost of each road remains unchanged over time. Other works on route planning and recommendation that have considered temporal factors simply assumed that the temporal dynamics be known in advance as a parametric function over time, which is not faithful to reality. To overcome these limitations, in this paper, we propose an extension to a previous static trajectory regression framework by learning the temporal dynamics of road travel costs in an innovative non-parametric manner which can effectively overcome the temporal sparsity problem. In particular, we unify multiple different trajectory regression problems in a multi-task framework by introducing a novel cross-task regularization which encourages temporal smoothness on the change of road travel costs. We then propose an efficient block coordinate descent method to solve the resulting problem by exploiting its separable structures and prove its convergence to global optimum. Experiments conducted on both synthetic and real data sets demonstrate the effectiveness of our method and its improved accuracy on travel time prediction.