Learning to Select: Problem, Solution, and Applications

Heechang Ryu, Donghyun Kim, Hayong Shin

Abstract: We propose a "Learning to Select" problem that selects the best among the flexible size candidates. This makes decisions based not only on the properties of the candidate, but also on the environment in which they belong to. For example, job dispatching in the manufacturing factory is a typical "Learning to Select" problem. We propose Variable-Length CNN which combines the classification power using hidden features from CNN and the idea of flexible input from Learning to Rank algorithms. This not only can handles flexible candidates using Dynamic Computation Graph, but also is computationally efficient because it only builds a network with the necessary sizes to fit the situation. We applied the algorithm to the job dispatching problem which uses the dispatching log data obtained from the virtual fine-tuned factory. Our proposed algorithm shows considerably better performance than other comparable algorithms.

Keywords: Selection Problem, Job Dispatching, Convolution Neural Network