Non-autoregressive Personalized Bundle Generation

Abstract

The personalized bundle generation problem, which aims to create a preferred bundle for user from numerous candidate items, receives increasing attention in recommendation. However, existing works ignore the order-invariant nature of the bundle and adopt sequential modeling methods as the solution, which might introduce inductive bias and cause a large latency in prediction. To address this problem, we propose to perform the bundle generation via non-autoregressive mechanism and design a novel encoder-decoder framework named BundleNAT, which can effectively output the targeted bundle in one-shot without relying on any inherent order. In detail, instead of learning sequential dependency, we propose to adopt pre-training techniques and graph neural network to fully embed user-based preference and item-based compatibility information, and use a self-attention based encoder to further extract global dependency pattern. We then design a permutation-equivariant decoding architecture that is able to directly output the desired bundle in a one-shot manner. Experiments on three real-world datasets from Youshu and Netease show the proposed BundleNAT significantly outperforms the current state-of-the-art methods in average by up to 35.92%, 10.97% and 23.67% absolute improvements in Precision, Precision+, and Recall, respectively.

Submitted to Information Processing & Management

References in corpus (17)

• BPR: Bayesian Personalized Ranking from Implicit Feedback
• LLaMA: Open and Efficient Foundation Language Models
• Recipe for a General, Powerful, Scalable Graph Transformer
• CrossCBR: Cross-view Contrastive Learning for Bundle Recommendation
• Personalized Bundle List Recommendation
• Understanding and Improving Lexical Choice in Non-Autoregressive Translation
• Incorporating BERT into Parallel Sequence Decoding with Adapters
• Attending to Graph Transformers
• Step-unrolled Denoising Autoencoders for Text Generation
• Adapting Multilingual Speech Representation Model for a New, Underresourced Language through Multilingual Fine-tuning and Continued Pretraining
• Your Transformer May Not be as Powerful as You Expect
• Self-Distillation Mixup Training for Non-autoregressive Neural Machine Translation
• Improving Non-autoregressive Generation with Mixup Training
• Accurate Bundle Matching and Generation via Multitask Learning with Partially Shared Parameters
• Fuzzy Alignments in Directed Acyclic Graph for Non-Autoregressive Machine Translation
• InsNet: An Efficient, Flexible, and Performant Insertion-based Text Generation Model
• Graph Positional and Structural Encoder