(SCC 2022) Context Preserving Data Augmentation for Sequential Recommendation

Benjamin Amankwata and Kenneth K Fletcher (University of Massachusetts Boston, USA)

Item representation learning is a fundamental task in Sequential Recommendation (SR). Effective representation is crucial for SR because they enable recommender systems to learn relevant relationships between items. SR researchers rely on User Historical Interactions (UHI) for effective item representations. However, UHI inherently suffers from data sparsity limitations that distort the item relationships and limit the learning of superior item representation. In this work, we seek to amplify weak item relation signals in UHI by augmenting each input sequence with a set of permutations that preserve both the local and global context. We employ a multi-layer bi-directional transformer encoder to learn superior contextualized item representations from the augmented data. Extensive experiments on benchmark datasets for next-item recommendations demonstrate that our proposed SR model can recover item relational dynamics distorted during the candidate generation process. In addition, our approach leads to learning superior item representations for many next-item state-of-the-art models employing RNNs and self-attention networks.