# Scaffolding Networks: Incremental Learning and Teaching Through Questioning

## TL;DR

The paper presents a novel incremental learning paradigm using a teacher-student neural network architecture that improves reasoning and understanding through sequential questioning and reinforcement learning.

## Contribution

It introduces the scaffolding network framework that enables machines to learn reasoning incrementally via interactive questioning and reinforcement learning, outperforming existing methods.

## Key findings

- Outperforms state-of-the-art methods on synthetic and real datasets
- Learns reasoning in a scalable way with minimal human input
- Demonstrates effective incremental learning through question-answer interactions

## Abstract

We introduce a new paradigm of learning for reasoning, understanding, and prediction, as well as the scaffolding network to implement this paradigm. The scaffolding network embodies an incremental learning approach that is formulated as a teacher-student network architecture to teach machines how to understand text and do reasoning. The key to our computational scaffolding approach is the interactions between the teacher and the student through sequential questioning. The student observes each sentence in the text incrementally, and it uses an attention-based neural net to discover and register the key information in relation to its current memory. Meanwhile, the teacher asks questions about the observed text, and the student network gets rewarded by correctly answering these questions. The entire network is updated continually using reinforcement learning. Our experimental results on synthetic and real datasets show that the scaffolding network not only outperforms state-of-the-art methods but also learns to do reasoning in a scalable way even with little human generated input.