Enabling Long-term Fairness in Dynamic Resource Allocation

We study the fairness of dynamic resource allocation problem under the α-fairness criterion. We recognize two different fairness objectives that naturally arise in this problem: the well-understood slot-fairness objective that aims to ensure fairness at every timeslot, and the less explored horizon-fairness objective that aims to ensure...

Lazy Lagrangians for Optimistic Learning With Budget Constraints

We consider the general problem of online convex optimization with time-varying budget constraints in the presence of predictions for the next cost and constraint functions, that arises in a plethora of network resource management problems. A novel saddle-point algorithm is designed by combining a Follow-The-Regularized-Leader iteration with...

Learning-based Reservation of Virtualized Network Resources

Network slicing markets have the potential to increase significantly the utilization of virtualized network resources and facilitate the low-cost deployment of over-the-top services. However, their success is conditioned on the service providers (SPs) being able to bid effectively for the virtualized resources. In this paper, we consider a...

Impact of Home-Based Learning Experience During COVID-19 on Future Intentions to Study Online: A Chinese University Perspective

As coronavirus disease 2019 (COVID-19) swept the world in early 2020, all the Chinese universities and colleges adopted online learning to fulfill the directive saying “classes suspended but learning continues.” Understanding the impact of this large-scale online learning experience on the future online learning intention of Chinese university...

Online Graph-Adaptive Learning with Scalability and Privacy

Graphs are widely adopted for modeling complex systems, including financial, biological, and social networks. Nodes in networks usually entail attributes, such as the age or gender of users in a social network. However, real-world networks can have very large size, and nodal attributes can be unavailable to a number of nodes, e.g., due to...

IntelliEye: Enhancing MOOC Learners' Video Watching Experience with Real-Time Attention Tracking

Massive Open Online Courses (MOOCs) have become an attractive opportunity for people around the world to gain knowledge and skills. Despite the initial enthusiasm of the first wave of MOOCs and the subsequent research efforts, MOOCs today suffer from retention issues: many MOOC learners start but do not finish. A main culprit is the lack of...

The TU Delft Online Learning Experience: From Theory to Practice

Last year, when we presented the OLE at the 2015 EDEN Conference in Barcelona, we were still at an early stage of its development, collecting fundamental background to support it and feedback from online learning experts. Although we only had a collection of ideas translated into 8 principles, it was clear that the model needed to be flexible in...

Gender and Diversity in Engineering MOOCs, a first Appraisal

Anytime, Anywhere – The development of an online course in Research Methodologies

Defining a Pedagogical Model: The TU Delft Online Learning Experience

In early 2014, the Delft University of Technology (TU Delft) started an innovation program with the aim to respond even more effectively to recent developments in open and online education. Drawing on the fields of Distance Education research and the university’s vision of the “engineer of the future”, TU Delft’s Extension School created a...

Online Learning Solutions for Freeway Travel Time Prediction

Providing travel time information to travelers on available route alternatives in traffic networks is widely believed to yield positive effects on individual drive behavior and (route/departure time) choice behavior, as well as on collective traffic operations in terms of, for example, overall time savings and—if nothing else—on the reliability...