We study user behavior in the courses offered by a major Massive Online Open Course (MOOC) provider during the summer of 2013. Since social learning is a key element of scalable education in MOOCs and is done via online discussion forums, our main focus is in understanding forum activities. Two salient features of MOOC forum activities drive our research: 1. High decline rate: for all courses studied, the volume of discussions in the forum declines continuously throughout the duration of the course. 2. High-volume, noisy discussions: at least 30% of the courses produce new discussion threads at rates that are infeasible for students or teaching staff to read through. Furthermore, a substantial portion of the discussions are not directly course-related.We investigate factors that correlate with the decline of activity in the online discussion forums and find effective strategies to classify threads and rank their relevance. Specifically, we use linear regression models to analyze the time series of the count data for the forum activities and make a number of observations, e.g., the teaching staff's active participation in the discussion increases the discussion volume but does not slow down the decline rate. We then propose a unified generative model for the discussion threads, which allows us both to choose efficient thread classifiers and design an effective algorithm for ranking thread relevance. Our ranking algorithm is further compared against two baseline algorithms, using human evaluation from Amazon Mechanical Turk.

No abstract

Federated learning (FedL) has emerged as a popular technique for distributing model training over a set of wireless devices, via iterative local updates (at devices) and global aggregations (at the server). In this paper, we develop parallel successive learning (PSL), which expands the FedL architecture along three dimensions: (i) Network, allowing decentralized cooperation among the devices via device-to-device (D2D) communications. (ii) Heterogeneity, interpreted at three levels: (ii-a) Learning: PSL considers heterogeneous number of stochastic gradient descent iterations with different mini-batch sizes at the devices; (ii-b) Data: PSL presumes a dynamic environment with data arrival and departure, where the distributions of local datasets evolve over time, captured via a new metric for model/concept drift. (ii-c) Device: PSL considers devices with different computation and communication capabilities. (iii) Proximity, where devices have different distances to each other and the access point. PSL considers the realistic scenario where global aggregations are conducted with idle times in-between them for resource efficiency improvements, and incorporates data dispersion and model dispersion with local model condensation into FedL. Our analysis sheds light on the notion of cold vs. warmed up models, and model inertia in distributed machine learning. We then propose networkaware dynamic model tracking to optimize the model learning vs. resource efficiency tradeoff, which we show is an NP-hard signomial programming problem. We finally solve this problem through proposing a general optimization solver. Our numerical results reveal new findings on the interdependencies between the idle times in-between the global aggregations, model/concept drift, and D2D cooperation configuration.

No abstract

No abstract