• Corpus ID: 245837581

Supervised Contrastive Learning for Recommendation

@article{Yang2022SupervisedCL,
  title={Supervised Contrastive Learning for Recommendation},
  author={Chun Yang},
  journal={ArXiv},
  year={2022},
  volume={abs/2201.03144}
}
  • Chun Yang
  • Published 10 January 2022
  • Computer Science
  • ArXiv
Compared with the traditional collaborative filtering methods, the graph convolution network can explicitly model the interaction between the nodes of the user-item bipartite graph and effectively use higher-order neighbor information, which enables the graph neural network to obtain more effective embeddings for recommendation, such as NGCF And LightGCN. However, its representations are very susceptible to the noise of interaction. In response to this problem, SGL explored the self-supervised… 

SPR: Supervised Personalized Ranking Based on Prior Knowledge for Recommendation

TLDR
The proposed novel loss function named Supervised Personalized Ranking (SPR) Based on Prior Knowledge improves the BPR loss by exploiting the prior knowledge on the interaction history of each user or item in the raw data.

SPR:S UPERVISED P ERSONALIZED R ANKING B ASED ON P RIOR K NOWLEDGE FOR R ECOMMENDATION

  • Computer Science
  • 2022
TLDR
The proposed novel loss function named Supervised Personalized Ranking (SPR) Based on Prior Knowledge improves the BPR loss by exploiting the prior knowledge on the interaction history of each user or item in the raw data.

References

SHOWING 1-10 OF 44 REFERENCES

LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation

TLDR
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.

Self-supervised Graph Learning for Recommendation

TLDR
This work explores self-supervised learning on user-item graph, so as to improve the accuracy and robustness of GCNs for recommendation, and implements it on the state-of-the-art model LightGCN, which has the ability of automatically mining hard negatives.

Neighbor Interaction Aware Graph Convolution Networks for Recommendation

TLDR
A novel framework NIA-GCN is proposed, which can explicitly model the relational information between neighbor nodes and exploit the heterogeneous nature of the user-item bipartite graph, and generalize to a commercial App store recommendation scenario.

Graph Convolutional Neural Networks for Web-Scale Recommender Systems

TLDR
A novel method based on highly efficient random walks to structure the convolutions and a novel training strategy that relies on harder-and-harder training examples to improve robustness and convergence of the model are developed.

Neural Graph Collaborative Filtering

TLDR
This work develops a new recommendation framework Neural Graph Collaborative Filtering (NGCF), which exploits the user-item graph structure by propagating embeddings on it, effectively injecting the collaborative signal into the embedding process in an explicit manner.

Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning

TLDR
It is shown that the graph convolution of the GCN model is actually a special form of Laplacian smoothing, which is the key reason why GCNs work, but it also brings potential concerns of over-smoothing with many convolutional layers.

Efficient Neural Matrix Factorization without Sampling for Recommendation

TLDR
This work derives three new optimization methods through rigorous mathematical reasoning, which can efficiently learn model parameters from the whole data with a rather low time complexity, and presents a general framework named ENMF, short for Efficient Neural Matrix Factorization.

Inductive Matrix Completion Based on Graph Neural Networks

TLDR
It is possible to train inductive matrix completion models without using side information while achieving similar or better performances than state-of-the-art transductive methods; local graph patterns around a (user, item) pair are effective predictors of the rating this user gives to the item; and long-range dependencies might not be necessary for modeling recommender systems.

Latent Relational Metric Learning via Memory-based Attention for Collaborative Ranking

TLDR
Qualitative studies demonstrate evidence that the proposed model is able to infer and encode explicit sentiment, temporal and attribute information despite being only trained on implicit feedback, ascertains the ability of LRML to uncover hidden relational structure within implicit datasets.

Collaborative Memory Network for Recommendation Systems

TLDR
Collaborative Memory Networks is proposed, a deep architecture to unify the two classes of CF models capitalizing on the strengths of the global structure of latent factor model and local neighborhood-based structure in a nonlinear fashion.