Masked and Swapped Sequence Modeling for Next Novel Basket Recommendation in Grocery Shopping (2023-08-02T00:00:00.000000Z)

TL;DR

A simple bi-directional transformer basket recommendation model (BTBR) is proposed, which is focused on directly modeling item-to-item correlations within and across baskets instead of learning complex basket representations.

Abstract

Next basket recommendation (NBR) is the task of predicting the next set of items based on a sequence of already purchased baskets. It is a recommendation task that has been widely studied, especially in the context of grocery shopping. In next basket recommendation (NBR), it is useful to distinguish between repeat items, i.e., items that a user has consumed before, and explore items, i.e., items that a user has not consumed before. Most NBR work either ignores this distinction or focuses on repeat items. We formulate the next novel basket recommendation (NNBR) task, i.e., the task of recommending a basket that only consists of novel items, which is valuable for both real-world application and NBR evaluation. We evaluate how existing NBR methods perform on the NNBR task and find that, so far, limited progress has been made w.r.t. the NNBR task. To address the NNBR task, we propose a simple bi-directional transformer basket recommendation model (BTBR), which is focused on directly modeling item-to-item correlations within and across baskets instead of learning complex basket representations. To properly train BTBR, we propose and investigate several masking strategies and training objectives: (i) item-level random masking, (ii) item-level select masking, (iii) basket-level all masking, (iv) basket-level explore masking, and (v) joint masking. In addition, an item-basket swapping strategy is proposed to enrich the item interactions within the same baskets. We conduct extensive experiments on three open datasets with various characteristics. The results demonstrate the effectiveness of BTBR and our masking and swapping strategies for the NNBR task. BTBR with a properly selected masking and swapping strategy can substantially improve NNBR performance.

Authors

References55 items

Learning to Ride a Buy-Cycle: A Hyper-Convolutional Model for Next Basket Repurchase Recommendation

ReCANet: A Repeat Consumption-Aware Neural Network for Next Basket Recommendation in Grocery Shopping

Flexible Order Aware Sequential Recommendation

Contrastive Learning for Sequential Recommendation

Self-Supervised Learning for Recommender Systems: A Survey

Learning Transferable User Representations with Sequential Behaviors via Contrastive Pre-training

A Next Basket Recommendation Reality Check

Modeling Dynamic Attributes for Next Basket Recommendation

Neural Basket Embedding for Sequential Recommendation

The World is Binary: Contrastive Learning for Denoising Next Basket Recommendation

Recurrent Convolution Basket Map for Diversity Next-Basket Recommendation

Dual Sequential Network for Temporal Sets Prediction

Recency Aware Collaborative Filtering for Next Basket Recommendation

Predicting Temporal Sets with Deep Neural Networks

Modeling Personalized Item Frequency Information for Next-basket Recommendation

Intention Nets: Psychology-Inspired User Choice Behavior Modeling for Next-Basket Prediction

Modeling Temporal Dynamics of Users’ Purchase Behaviors for Next Basket Prediction

Correlation-Sensitive Next-Basket Recommendation

Sequential Recommender Systems: Challenges, Progress and Prospects

Sets2Sets: Learning from Sequential Sets with Neural Networks

Are we really making much progress? A worrying analysis of recent neural recommendation approaches

BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer

Session-based Recommendation with Graph Neural Networks

Representing and Recommending Shopping Baskets with Complementarity, Compatibility and Loyalty

Self-Attentive Sequential Recommendation

STAMP: Short-Term Attention/Memory Priority Model for Session-based Recommendation

An Attribute-aware Neural Attentive Model for Next Basket Recommendation

Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding

Neural Attentive Session-based Recommendation

Recurrent Neural Networks with Top-k Gains for Session-based Recommendations

Attention is All you Need

Diversity, Serendipity, Novelty, and Coverage

Layer Normalization

A Dynamic Recurrent Model for Next Basket Recommendation

Bridging Nonlinearities and Stochastic Regularizers with Gaussian Error Linear Units

Deep Residual Learning for Image Recognition

Session-based Recommendations with Recurrent Neural Networks

On the Properties of Neural Machine Translation: Encoder–Decoder Approaches

Factorizing personalized Markov chains for next-basket recommendation

Learning to Forget: Continual Prediction with LSTM

“Cloze Procedure”: A New Tool for Measuring Readability

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Novelty, and Coverage: A Survey and Empirical Analysis of Beyond-accuracy Objectives in Recommender Systems

Dropout: a simple way to prevent neural networks from overfitting

The Graph Neural Network Model

Evaluating collaborative filtering recommender systems

This is a NNBR-specific masking strategy

Random : This is a conventional masking strategy, which has been adopted in BERT4Rec [31]. Specifically

1) Multi-head attention layer , which adopts the popular attention mechanism [36] and aggregates all items’ embeddings across different baskets with adaptive weights

position according to mask ratio 𝛼 as input

RQ3 Does the swapping strategy contribute to the improvements?

RQ4 How do the hyper-parameters influence the models’ performance and how different masking strategies affect the training dynamics?

novel items in the last basket as training labels (Train-explore). Configurations.

RQ2 How does BTBR with different masking strategies perform compared to the state-of-the-art models?

RecSys ’23, September 18–22, 2023, Singapore, Singapore