Learning Markov Chain in Unordered Dataset

TL;DR

This paper introduces OrderNet, an unsupervised method to uncover the hidden order in datasets by learning a Markov chain model, enabling better understanding and application of unordered data.

Contribution

It proposes a neural network-based approach to learn the transition operator of an underlying Markov chain from unordered data, with a novel permutation scheme for efficient training.

Findings

OrderNet can successfully discover data orderings in various datasets.

The method generalizes well to unseen instances.

OrderNet improves performance in one-shot recognition tasks.

Abstract

The assumption that data samples are independently identically distributed is the backbone of many learning algorithms. Nevertheless, datasets often exhibit rich structure in practice, and we argue that there exist some unknown order within the data instances. In this technical report, we introduce OrderNet that can be used to extract the order of data instances in an unsupervised way. By assuming that the instances are sampled from a Markov chain, our goal is to learn the transitional operator of the underlying Markov chain, as well as the order by maximizing the generation probability under all possible data permutations. Specifically, we use neural network as a compact and soft lookup table to approximate the possibly huge, but discrete transition matrix. This strategy allows us to amortize the space complexity with a single model. Furthermore, this simple and compact representation also provides a short description to the dataset and generalizes to unseen instances as well. To ensure that the learned Markov chain is ergodic, we propose a greedy batch-wise permutation scheme that allows fast training. Empirically, we show that OrderNet is able to discover an order among data instances. We also extend the proposed OrderNet to one-shot recognition task and demonstrate favorable results.