On parallelizing SGD for pairwise learning to rank in collaborative filtering recommender systems

Learning to rank with pairwise loss functions has been found useful in collaborative filtering recommender systems. At web scale, the optimization is often based on matrix factorization with stochastic gradient descent (SGD) which has a sequential nature. We investigate two different shared memory lock-free parallel SGD schemes based on block partitioning and no partitioning for use with pairwise loss functions. To speed up convergence to a solution, we extrapolate simple practical algorithms from their application to pointwise learning to rank. Experimental results show that the proposed algorithms are quite useful regarding their ranking ability and speedup patterns in comparison to their sequential counterpart.