Towards explainable networked prediction

Abstract

Networked prediction has attracted lots of research attention in recent years. Compared with the traditional learning setting, networked prediction is even harder to understand due to its coupled, multi-level nature. The learning process propagates top-down through the underlying network from the macro level (the entire learning system), to meso level (learning tasks), and to micro level (individual learning examples). In the meanwhile, the networked prediction setting also offers rich context to explain the learning process through the lens of multi-aspect, including training examples (e.g., what are the most influential examples), the learning tasks (e.g., which tasks are most important) and the task network (e.g., which task connections are the keys). Thus, we propose a multi-aspect, multi-level approach to explain networked prediction. The key idea is to efficiently quantify the influence on different levels the learning system due to the perturbation of various aspects. Th proposed method offers two distinctive advantages: (1) multi-aspe multi-level: it is able to explain networked prediction from multip aspects (i.e., example-task-network) at multiple levels (i.e., macr meso-micro); (2) efficiency: it has a linear complexity by efficient evaluating the influences of changes to the networked predictio without retraining.