Neural Collaborative Reasoning

Abstract

Existing Collaborative Filtering (CF) methods are mostly designed based on the idea of matching, i.e., by learning user and item embeddings from data using shallow or deep models, they try to capture the associative relevance patterns in data, so that a user embedding can be matched with relevant item embeddings using designed or learned similarity functions. However, as a cognition rather than a perception intelligent task, recommendation requires not only the ability of pattern recognition and matching from data, but also the ability of cognitive reasoning in data. In this paper, we propose to advance Collaborative Filtering (CF) to Collaborative Reasoning (CR), which means that each user knows part of the reasoning space, and they collaborate for reasoning in the space to estimate preferences for each other. Technically, we propose a Neural Collaborative Reasoning (NCR) framework to bridge learning and reasoning. Specifically, we integrate the power of representation learning and logical reasoning, where representations capture similarity patterns in data from perceptual perspectives, and logic facilitates cognitive reasoning for informed decision making. An important challenge, however, is to bridge differentiable neural networks and symbolic reasoning in a shared architecture for optimization and inference. To solve the problem, we propose a modularized reasoning architecture, which learns logical operations such as AND ($\wedge$), OR ($\vee$) and NOT ($\neg$) as neural modules for implication reasoning ($\to$). In this way, logical expressions can be equivalently organized as neural networks, so that logical reasoning and prediction can be conducted in a continuous space. Experiments on real-world datasets verified the advantages of our framework compared with both shallow, deep and reasoning models.

Accepted to the 30th Web Conference (WWW 2021)

References in corpus (9)

• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Translation-based Recommendation
• The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
• Neural-Symbolic Learning and Reasoning: A Survey and Interpretation
• DKN: Deep Knowledge-Aware Network for News Recommendation
• Neural Logic Machines
• Efficient Probabilistic Logic Reasoning with Graph Neural Networks
• Critically Examining the Claimed Value of Convolutions over User-Item Embedding Maps for Recommender Systems
• Neural Logic Reinforcement Learning

Cited by in corpus (22)

• Personalized Counterfactual Fairness in Recommendation
• Counterfactual Explainable Recommendation
• Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning
• Multi-Behavior Graph Neural Networks for Recommender System
• How to Index Item IDs for Recommendation Foundation Models
• Explainable Fairness in Recommendation
• Exploration and Regularization of the Latent Action Space in Recommendation
• Graph Collaborative Reasoning
• Efficient Non-Sampling Knowledge Graph Embedding
• Causal Collaborative Filtering
• Counterfactual Collaborative Reasoning
• Dynamic Causal Collaborative Filtering
• RGRecSys: A Toolkit for Robustness Evaluation of Recommender Systems
• AutoLossGen: Automatic Loss Function Generation for Recommender Systems
• Variation Control and Evaluation for Generative SlateRecommendations
• A Multi-Channel Next POI Recommendation Framework with Multi-Granularity Check-in Signals
• Personalized Transformer for Explainable Recommendation
• Differentiable Fuzzy Neural Networks for Recommender Systems
• Learn Basic Skills and Reuse: Modularized Adaptive Neural Architecture Search (MANAS)
• EXTRA: Explanation Ranking Datasets for Explainable Recommendation
• Explainable Recommendation with Simulated Human Feedback
• Problem Learning: Towards the Free Will of Machines