Human-Guided Learning of Column Networks: Augmenting Deep Learning with Advice

Abstract

Recently, deep models have been successfully applied in several applications, especially with low-level representations. However, sparse, noisy samples and structured domains (with multiple objects and interactions) are some of the open challenges in most deep models. Column Networks, a deep architecture, can succinctly capture such domain structure and interactions, but may still be prone to sub-optimal learning from sparse and noisy samples. Inspired by the success of human-advice guided learning in AI, especially in data-scarce domains, we propose Knowledge-augmented Column Networks that leverage human advice/knowledge for better learning with noisy/sparse samples. Our experiments demonstrate that our approach leads to either superior overall performance or faster convergence (i.e., both effective and efficient).

Under Review at 'Machine Learning Journal' (MLJ)

References in corpus (6)

• Semi-Supervised Classification with Graph Convolutional Networks
• Playing Atari with Deep Reinforcement Learning
• Inductive Representation Learning on Large Graphs
• Interaction Networks for Learning about Objects, Relations and Physics
• Lifted Relational Neural Networks
• RelNN: A Deep Neural Model for Relational Learning