Broad Recommender System: An Efficient Nonlinear Collaborative Filtering Approach

TL;DR

BroadCF tackles the heavy training cost of nonlinear collaborative filtering by substituting deep nets with Broad Learning System (BLS) and a novel data-preprocessing pipeline. The approach converts sparse rating data into low-dimensional, information-rich inputs via KNU and LNI-based rating vectors, enabling efficient nonlinear mapping through BLS with mapped and enhanced feature layers. Training relies on a ridge-regression pseudoinverse, yielding a small parameter footprint while achieving state-of-the-art or competitive RMSE/MAE and NDCG/HR across seven datasets, with substantially lower memory and time costs than DNN-based models. The work demonstrates practical scalability for large-scale recommendations and suggests future extensions to leverage auxiliary data and cross-domain scenarios.

Abstract

Recently, Deep Neural Networks (DNNs) have been widely introduced into Collaborative Filtering (CF) to produce more accurate recommendation results due to their capability of capturing the complex nonlinear relationships between items and users.However, the DNNs-based models usually suffer from high computational complexity, i.e., consuming very long training time and storing huge amount of trainable parameters. To address these problems, we propose a new broad recommender system called Broad Collaborative Filtering (BroadCF), which is an efficient nonlinear collaborative filtering approach. Instead of DNNs, Broad Learning System (BLS) is used as a mapping function to learn the complex nonlinear relationships between users and items, which can avoid the above issues while achieving very satisfactory recommendation performance. However, it is not feasible to directly feed the original rating data into BLS. To this end, we propose a user-item rating collaborative vector preprocessing procedure to generate low-dimensional user-item input data, which is able to harness quality judgments of the most similar users/items. Extensive experiments conducted on seven benchmark datasets have confirmed the effectiveness of the proposed BroadCF algorithm

Figures (7)

• Figure 1: Illustration of the proposed BroadCF algorithm.
• Figure 2: Hyper-parameter analysis: The results in terms of RMSE achieved by BroadCF with different ${k}$ and $l$.
• Figure 3: Hyper-parameter analysis: The results in terms of MAE achieved by BroadCF with different ${k}$ and $l$.
• Figure 4: Hyper-parameter analysis: The results in terms of RMSE and MAE achieved by BroadCF with different $n$.
• Figure 5: Hyper-parameter analysis: The results in terms of RMSE and MAE achieved by BroadCF with different $d_z$.