Conv4Rec: A 1-by-1 Convolutional AutoEncoder for User Profiling through Joint Analysis of Implicit and Explicit Feedbacks

2025-09-09

AI Summary

This work addresses two key challenges in recommender systems: the difficulty of jointly modeling explicit ratings and implicit feedback, and the lack of interpretability in predictions. To this end, we propose a unified framework based on a 1×1 convolutional autoencoder. The model employs a joint loss function to simultaneously optimize the probability of content consumption (implicit feedback) and the probability of receiving high ratings (explicit feedback). Notably, we derive the first generalization error bound for autoencoders in recommendation tasks, ensuring theoretical recoverability of the sampling distribution. The approach yields fine-grained probabilistic outputs, substantially improving user preference characterization. Evaluated on multiple real-world datasets, the single model achieves state-of-the-art performance for both explicit and implicit feedback prediction, while enhancing result interpretability through principled probabilistic modeling and theoretically grounded optimization.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Reasoning under Uncertainty: Relational Probabilistic Models
• Data Mining & Knowledge Management: Recommender Systems

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

We introduce a new convolutional AutoEncoder architecture for user modelling and recommendation tasks with several improvements over the state of the art. Firstly, our model has the flexibility to learn a set of associations and combinations between different interaction types in a way that carries over to each user and item. Secondly, our model is able to learn jointly from both the explicit ratings and the implicit information in the sampling pattern (which we refer to as `implicit feedback'). It can also make separate predictions for the probability of consuming content and the likelihood of granting it a high rating if observed. This not only allows the model to make predictions for both the implicit and explicit feedback, but also increases the informativeness of the predictions: in particular, our model can identify items which users would not have been likely to consume naturally, but would be likely to enjoy if exposed to them. Finally, we provide several generalization bounds for our model, which to the best of our knowledge, are among the first generalization bounds for auto-encoders in a Recommender Systems setting; we also show that optimizing our loss function guarantees the recovery of the exact sampling distribution over interactions up to a small error in total variation. In experiments on several real-life datasets, we achieve state-of-the-art performance on both the implicit and explicit feedback prediction tasks despite relying on a single model for both, and benefiting from additional interpretability in the form of individual predictions for the probabilities of each possible rating.

Problem

• Jointly modeling implicit and explicit feedbacks for recommendation
• Predicting content consumption and high rating probabilities separately
• Learning user-item associations through convolutional autoencoder architecture

Innovation

• 1-by-1 convolutional AutoEncoder architecture
• Joint learning from explicit and implicit feedback
• Separate predictions for consumption and rating probabilities