Causal Incremental Graph Convolution for Recommender System Retraining

  title={Causal Incremental Graph Convolution for Recommender System Retraining},
  author={Sihao Ding and Fuli Feng and Xiangnan He and Yong Liao and Jun Shi and Yongdong Zhang},
  journal={IEEE transactions on neural networks and learning systems},
The real-world recommender system needs to be regularly retrained to keep with the new data. In this work, we consider how to efficiently retrain graph convolution network (GCN)-based recommender models that are state-of-the-art techniques for the collaborative recommendation. To pursue high efficiency, we set the target as using only new data for model updating, meanwhile not sacrificing the recommendation accuracy compared with full model retraining. This is nontrivial to achieve since the… 

Figures and Tables from this paper

Continual Graph Learning: A Survey

This survey introduces the basic concepts of CGL and highlights two unique challenges brought by graphs, and reviews and categorizes recent state-of-the-art approaches, analyzing their strategies to tackle the unique challenges in CGL.

A Comparative Analysis of Bias Amplification in Graph Neural Network Approaches for Recommender Systems

This paper aims to comprehensively study the bias amplification issue through a literature review and an analysis of the behavior against biases of different GNN-based algorithms compared to state-of-the-art methods.

Mitigating Confounding Bias for Recommendation via Counterfactual Inference

A novel CIDR framework that enables the analysis of causes of biases from a causal perspective and boosts counterfactual inference to eliminate the causal-effect of such confounders in order to achieve a satisfactory recommendation.

Debiased Recommendation with User Feature Balancing

This research presents a parallel version of the Noah’s Ark algorithm that automates the very labor-intensive and therefore time-heavy and expensive and expensive process of designing and implementing Noah's Ark-like algorithms.

Uncovering Main Causalities for Long-tailed Information Extraction

The proposed counterfactual IE (CFIE) is a novel framework that aims to uncover the main causalities behind data in the view of causal inference, and introduces a unified structural causal model for various IE tasks, describing the relationships among variables.



Overcoming catastrophic forgetting in neural networks

It is shown that it is possible to overcome the limitation of connectionist models and train networks that can maintain expertise on tasks that they have not experienced for a long time and selectively slowing down learning on the weights important for previous tasks.

Distilling Causal Effect of Data in Class-Incremental Learning

The proposed causal effect distillation method can improve various state-of-the-art CIL methods by a large margin and capture the Incremental Momentum Effect of the data stream, which can help to retain the old effect overwhelmed by the new data effect, and thus alleviate the forgetting of the old class in testing.

Causal Inference in Statistics: A Primer

Judea Pearl presents a book ideal for beginners in statistics, providing a comprehensive introduction to the field of causality, with examples from classical statistics presented throughout to demonstrate the need for causality in resolving decision-making dilemmas posed by data.

How to Retrain Recommender System?: A Sequential Meta-Learning Method

This work proposes a new training method, aiming to abandon the historical data during retraining through learning to transfer the past training experience, and designs a neural network-based transfer component, which transforms the old model to a new model that is tailored for future recommendations.

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.

Neural Graph Collaborative Filtering

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.

Combining Graph Neural Networks With Expert Knowledge for Smart Contract Vulnerability Detection

This paper casts the rich control- and data- flow semantics of the source code into a contract graph and proposes a novel temporal message propagation network to extract the graph feature from the normalized graph, and combines expert patterns with designed expert patterns to yield a final detection system.

Empowering Language Understanding with Counterfactual Reasoning

A Counterfactual Reasoning Model is proposed, which mimics the counterfactual thinking by learning from fewcounterfactual samples, and is validated on sentiment analysis and natural language inference.

Deconfounded Video Moment Retrieval with Causal Intervention

A causality-inspired VMR framework is proposed that builds structural causal model to capture the true effect of query and video content on the prediction, and a Deconfounded Cross-modal Matching method is developed to remove the confounding effects of moment location.

Deconfounded Recommendation for Alleviating Bias Amplification

This work scrutinizes the cause-effect factors for bias amplification, identifying the main reason lies in the confounding effect of imbalanced item distribution on user representation and prediction score, and proposes a Deconfounded Recommender System (DecRS), which models the causal effect of user representation on the prediction score.