Unsupervised Semantic Hashing with Pairwise Reconstruction

TL;DR

This paper introduces PairRec, a novel unsupervised semantic hashing method using pairwise reconstruction with a variational autoencoder, leading to improved document similarity search performance.

Contribution

The paper proposes PairRec, a new hashing model that encodes weakly supervised pairs and reconstructs documents to better preserve local neighborhood structures.

Findings

Significant performance improvements over existing methods

Effective encoding of local neighborhood structures

Enhanced document similarity search accuracy

Abstract

Semantic Hashing is a popular family of methods for efficient similarity search in large-scale datasets. In Semantic Hashing, documents are encoded as short binary vectors (i.e., hash codes), such that semantic similarity can be efficiently computed using the Hamming distance. Recent state-of-the-art approaches have utilized weak supervision to train better performing hashing models. Inspired by this, we present Semantic Hashing with Pairwise Reconstruction (PairRec), which is a discrete variational autoencoder based hashing model. PairRec first encodes weakly supervised training pairs (a query document and a semantically similar document) into two hash codes, and then learns to reconstruct the same query document from both of these hash codes (i.e., pairwise reconstruction). This pairwise reconstruction enables our model to encode local neighbourhood structures within the hash code directly through the decoder. We experimentally compare PairRec to traditional and state-of-the-art approaches, and obtain significant performance improvements in the task of document similarity search.