One-Shot Learning on Attributed Sequences

TL;DR

This paper introduces OLAS, a deep learning framework for one-shot learning on attributed sequences, addressing complex real-world data with attribute-sequence dependencies, and demonstrates its superior performance over existing methods.

Contribution

The paper proposes a novel deep learning framework OLAS for one-shot learning on attributed sequences, handling complex data with attribute-sequence dependencies.

Findings

OLAS outperforms state-of-the-art methods on real-world datasets.

The framework effectively models dependencies between attributes and sequences.

Empirical results show robustness across various parameter settings.

Abstract

One-shot learning has become an important research topic in the last decade with many real-world applications. The goal of one-shot learning is to classify unlabeled instances when there is only one labeled example per class. Conventional problem setting of one-shot learning mainly focuses on the data that is already in feature space (such as images). However, the data instances in real-world applications are often more complex and feature vectors may not be available. In this paper, we study the problem of one-shot learning on attributed sequences, where each instance is composed of a set of attributes (e.g., user profile) and a sequence of categorical items (e.g., clickstream). This problem is important for a variety of real-world applications ranging from fraud prevention to network intrusion detection. This problem is more challenging than conventional one-shot learning since there are dependencies between attributes and sequences. We design a deep learning framework OLAS to tackle this problem. The proposed OLAS utilizes a twin network to generalize the features from pairwise attributed sequence examples. Empirical results on real-world datasets demonstrate the proposed OLAS can outperform the state-of-the-art methods under a rich variety of parameter settings.