Sample Enrichment via Temporary Operations on Subsequences for Sequential Recommendation

TL;DR

This paper introduces SETO, a model-agnostic framework that enhances sequential recommendation by temporarily enriching data transformations through subsequence operations, improving performance without extra data or complex models.

Contribution

The paper proposes a novel, generic framework called SETO that enriches transformation space via subsequence operations, avoiding extra data and complex models in sequential recommendation.

Findings

SETO improves performance across multiple models and datasets.

It demonstrates versatility over state-of-the-art sequential recommendation models.

Effective on real-world and large-scale industry datasets.

Abstract

Sequential recommendation leverages interaction sequences to predict forthcoming user behaviors, crucial for crafting personalized recommendations. However, the true preferences of a user are inherently complex and high-dimensional, while the observed data is merely a simplified and low-dimensional projection of the rich preferences, which often leads to prevalent issues like data sparsity and inaccurate model training. To learn true preferences from the sparse data, most existing works endeavor to introduce some extra information or design some ingenious models. Although they have shown to be effective, extra information usually increases the cost of data collection, and complex models may result in difficulty in deployment. Innovatively, we avoid the use of extra information or alterations to the model; instead, we fill the transformation space between the observed data and the underlying preferences with randomness. Specifically, we propose a novel model-agnostic and highly generic framework for sequential recommendation called sample enrichment via temporary operations on subsequences (SETO), which temporarily and separately enriches the transformation space via sequence enhancement operations with rationality constraints in training. The transformation space not only exists in the process from input samples to preferences but also in preferences to target samples. We highlight our SETO's effectiveness and versatility over multiple representative and state-of-the-art sequential recommendation models (including six single-domain sequential models and two cross-domain sequential models) across multiple real-world datasets (including three single-domain datasets, three cross-domain datasets and a large-scale industry dataset).