Scenario-Adaptive and Self-Supervised Model for Multi-Scenario Personalized Recommendation
arXiv:2208.11457 · doi:10.1145/3511808.3557154
Abstract
Multi-scenario recommendation is dedicated to retrieve relevant items for users in multiple scenarios, which is ubiquitous in industrial recommendation systems. These scenarios enjoy portions of overlaps in users and items, while the distribution of different scenarios is different. The key point of multi-scenario modeling is to efficiently maximize the use of whole-scenario information and granularly generate adaptive representations both for users and items among multiple scenarios. we summarize three practical challenges which are not well solved for multi-scenario modeling: (1) Lacking of fine-grained and decoupled information transfer controls among multiple scenarios. (2) Insufficient exploitation of entire space samples. (3) Item's multi-scenario representation disentanglement problem. In this paper, we propose a Scenario-Adaptive and Self-Supervised (SASS) model to solve the three challenges mentioned above. Specifically, we design a Multi-Layer Scenario Adaptive Transfer (ML-SAT) module with scenario-adaptive gate units to select and fuse effective transfer information from whole scenario to individual scenario in a quite fine-grained and decoupled way. To sufficiently exploit the power of entire space samples, a two-stage training process including pre-training and fine-tune is introduced. The pre-training stage is based on a scenario-supervised contrastive learning task with the training samples drawn from labeled and unlabeled data spaces. The model is created symmetrically both in user side and item side, so that we can get distinguishing representations of items in different scenarios. Extensive experimental results on public and industrial datasets demonstrate the superiority of the SASS model over state-of-the-art methods. This model also achieves more than 8.0% improvement on Average Watching Time Per User in online A/B tests.
Accepted by CIKM 2022
References in corpus (16)
- Efficient Estimation of Word Representations in Vector Space
- A Simple Framework for Contrastive Learning of Visual Representations
- Self-supervised Graph Learning for Recommendation
- S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization
- CoNet: Collaborative Cross Networks for Cross-Domain Recommendation
- Embedding-based Retrieval in Facebook Search
- BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
- SAR-Net: A Scenario-Aware Ranking Network for Personalized Fair Recommendation in Hundreds of Travel Scenarios
- Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction
- Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate
- DDTCDR: Deep Dual Transfer Cross Domain Recommendation
- SDM: Sequential Deep Matching Model for Online Large-scale Recommender System
- One Model to Serve All: Star Topology Adaptive Recommender for Multi-Domain CTR Prediction
- Leaving No One Behind: A Multi-Scenario Multi-Task Meta Learning Approach for Advertiser Modeling
- MiNet: Mixed Interest Network for Cross-Domain Click-Through Rate Prediction
- Contrastive Cross-domain Recommendation in Matching