FIRE: knowledge-enhanced recommendation with feature interaction and intent-aware attention networks

Abstract

To solve the information overload issue and enhance the user experience of various web applications, recommender systems aim to better model user interests and preferences. Knowledge Graphs (KGs), consisting of real-world objective facts and fruitful entities, play a vital role in recommender systems. Recently, a technological trend has been to develop end-to-end Graph Neural Networks (GNNs)-based knowledge-aware recommendation (a.k.a., Knowledge Graph Recommendation, KGR) models. Unfortunately, current GNNs-based KGR approaches focus on how to capture high-order feature information on KGs while neglecting the following two crucial limitations: 1) The explicitly high-order feature interaction and fusion mechanism and 2) The valid user intent modelling mechanism. As such, these issues lead to insufficient user/item representation learning capability and unsatisfactory KGR performance. In this work, we present a novel Knowledge-enhanced Re commendation with F eature I nteraction and Intent-aware Attention Networks (FIRE) to address the latent intent modelling and high-order feature interaction deficiencies ignored by existing KGR methods. Based on the prototype user/item representation learning leveraging the GNNs-based approach, our model offers the following major improvements: One is the innovative use of Convolutional Neural Networks (CNNs) that perform vertical convolutional (a.k.a., bit-level convolutional) and horizontal convolutional (a.k.a., vector-level convolutional) processes to model multi-granular high-order feature interactions to enhance item-side representation learning. Another is to model users’ latent intent factors by utilizing a two-level attention mechanism (i.e., node- and intent-level attention mechanism) to enhance user-side representation learning. Extensive experiments on three KGs domain public datasets demonstrate that our method outperforms the existing state-of-the-art baseline. Last but not least, numerous ablation- and model studies demystify the working mechanism and elucidate the plausibility of the proposed model.

KEMIM: Knowledge-Enhanced User Multi-Interest Modeling for Recommender Systems

“…CG-KGR [37] encapsulates historical interactions to construct an interactive information summarization, and adopts Collaborative Guidance Mechanism to extract information. FIRE [40] models multi-granular high-order feature interactions by convolutional neural networks (CNNs) and the users' latent intent factors by utilizing a two-level attention mechanism to improve user and item representation learning.…”

Human Expert Based Technologies to Support Knowledge Discovery

“…Expert systems are usually equipped with data mining, machine learning, reasoning and decision making [1,2,3]. Data mining is actually a gradual evolutionary process.…”

Intelligent Control Over Multiple Ovens by Connection Models

“…Neural networks are widely used in modeling and control, mainly because neural networks have the ability to approximate arbitrary nonlinear mapping, parallel distributed computing, adaptive self-learning and fault tolerance, and are essentially a multi-variable process [1,2,3,4]. The role of neural network in control can be divided into several categories: the first type is the model that acts as the object in various control structures based on the model; the second type is the controller; the third type is the optimization calculation role in the control system; the fourth type is the fusion of other intelligent control methods, such as expert system and fuzzy control, to provide it with non-parametric object model and inference model [5,6,7].…”