Hyper Meta-Path Contrastive Learning for Multi-Behavior Recommendation

@article{Yang2021HyperMC,
  title={Hyper Meta-Path Contrastive Learning for Multi-Behavior Recommendation},
  author={Haoran Yang and Hongxu Chen and Lin Li and Philip S. Yu and Guandong Xu},
  journal={2021 IEEE International Conference on Data Mining (ICDM)},
  year={2021},
  pages={787-796}
}
User purchasing prediction with multi-behavior information remains a challenging problem for current recommendation systems. Various methods have been proposed to address it via leveraging the advantages of graph neural networks (GNNs) or multi-task learning. However, most existing works do not take the complex dependencies among different behaviors of users into consideration. They utilize simple and fixed schemes, like neighborhood information aggregation or mathematical calculation of… 

Figures and Tables from this paper

Multi-Behavior Hypergraph-Enhanced Transformer for Sequential Recommendation

A Multi-Behavior Hypergraph-enhanced T ransformer framework (MBHT) to capture both short-term and long-term cross-type behavior dependencies, and incorporates the global multi-behavior dependency into the hypergraph neural architecture to capture the hierarchical long-range item correlations in a customized manner.

Self-Supervised Hypergraph Transformer for Recommender Systems

SHT, a novel Self-Supervised Hypergraph Transformer framework (SHT) which augments user representations by exploring the global collaborative relationships in an explicit way, is proposed for data augmentation over the user-item interaction graph, so as to enhance the robustness of recommender systems.

Self-Supervised Learning for Recommendation

This tutorial aims to provide a systemic review of state-of-the-art SSL-based recommender systems in terms of recommendation scenarios, and summarizes and categorizes existing work of SSL- based recommender Systems in termsof recommendation scenarios.

Self-Supervised Learning for Recommender Systems: A Survey

An exclusive definition of SSR is proposed, on top of which a comprehensive taxonomy is built to divide existing SSR methods into four categories: contrastive, generative, predictive, and hybrid.

HICF: Hyperbolic Informative Collaborative Filtering

A novel learning method, named hyperbolic informative collaborative learning (HICF), aiming to compensate for the recommendation effectiveness of the head item while at the same time improving the performance of the tail item is designed.

Federated Graph Contrastive Learning

This paper investigates how to implement differential privacy on graph edges and observes the performances decreasing in the experiments, and proposes to leverage the advantages of graph contrastive learning to alleviate the performance dropping caused by differential privacy.

Dual Space Graph Contrastive Learning

A novel graph contrastive learning method, namely Dual Space Graph Contrastive (DSGC) Learning is proposed, to conduct graph Contrastive learning among views generated in different spaces including the hyperbolic space and the Euclidean space to bridge the spaces and leverage advantages from both sides.

Hyperbolic Graph Representation Learning: A Tutorial

This tutorial aims to give an introduction to this emerging emerging form of graph representation learning, by comprehensively revisit the hyperbolic embedding techniques includingHyperbolic shallow models and hyperbolicsneural networks, and the technical details of the currenthyperbolicgraph neural networks.

Dual-Task Learning for Multi-Behavior Sequential Recommendation

A novel framework named NextIP is proposed that adopts a dual-task learning strategy to convert the problem to two specific tasks, i.e., next-item prediction and purchase prediction, and performs significantly better than the state-of-the-art methods.

References

SHOWING 1-10 OF 33 REFERENCES

Next-item Recommendation with Sequential Hypergraphs

The proposed model can significantly outperform the state-of-the-art in predicting the next interesting item for each user and is equipped with a fusion layer to incorporate both the dynamic item embedding and short-term user intent to the representation of each interaction.

Learning to Recommend With Multiple Cascading Behaviors

A neural network model is developed to capture the complicated and multi-type interactions between users and items and shows that modeling multiple behaviors is particularly useful for providing recommendation for sparse users that have very few interactions.

Multi-level Hyperedge Distillation for Social Linking Prediction on Sparsely Observed Networks

This work presents a novel hypergraph neural networks named HNN, which takes the multi-level hypergraphs as input and makes the node embeddings smooth on hyperedges instead of pair-wise links only, and introduces the hypergraph to uncover higher-level relations, which is exceptionally crucial to deduce unobserved links.

LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation

This work proposes a new model named LightGCN, including only the most essential component in GCN -- neighborhood aggregation -- for collaborative filtering, and is much easier to implement and train, exhibiting substantial improvements over Neural Graph Collaborative Filtering (NGCF) under exactly the same experimental setting.

Temporal Meta-path Guided Explainable Recommendation

This paper proposes a novel Temporal Meta-path Guided Explainable Recommendation (TMER), which utilizes well-designed item-item path modelling between consecutive items with attention mechanisms to sequentially model dynamic user-item evolutions on dynamic knowledge graph for explainable recommendations.

Heterogeneous Information Network Embedding for Recommendation

A novel heterogeneous network embedding based approach for HIN based recommendation, called HERec is proposed, which shows the capability of the HERec model for the cold-start problem, and reveals that the transformed embedding information from HINs can improve the recommendation performance.

Efficient Heterogeneous Collaborative Filtering without Negative Sampling for Recommendation

This work proposes a novel non-sampling transfer learning solution, named Efficient Heterogeneous Collaborative Filtering (EHCF) for Top-N recommendation that can not only model fine-grained user-item relations, but also efficiently learn model parameters from the whole heterogeneous data with a rather low time complexity.

Meta-Graph: Few shot Link Prediction via Meta Learning

A new gradient-based meta learning framework, Meta-Graph, that can learn to quickly adapt to a new graph using only a small sample of true edges, enabling not only fast adaptation but also improved results at convergence.

Billion-scale Recommendation with Heterogeneous Side Information at Taobao

This work presents a flexible and highly scalable Side Information (SI) enhanced Skip-Gram (SISG) framework, which is deployed at Taobao and demonstrates the significant superiority of SISG over the previously deployed framework, EGES, and a well-tuned CF.

metapath2vec: Scalable Representation Learning for Heterogeneous Networks

Two scalable representation learning models, namely metapath2vec and metapATH2vec++, are developed that are able to not only outperform state-of-the-art embedding models in various heterogeneous network mining tasks, but also discern the structural and semantic correlations between diverse network objects.