Linear, or Non-Linear, That is the Question!

by   Taeyong Kong, et al.

There were fierce debates on whether the non-linear embedding propagation of GCNs is appropriate to GCN-based recommender systems. It was recently found that the linear embedding propagation shows better accuracy than the non-linear embedding propagation. Since this phenomenon was discovered especially in recommender systems, it is required that we carefully analyze the linearity and non-linearity issue. In this work, therefore, we revisit the issues of i) which of the linear or non-linear propagation is better and ii) which factors of users/items decide the linearity/non-linearity of the embedding propagation. We propose a novel Hybrid Method of Linear and non-linEar collaborative filTering method (HMLET, pronounced as Hamlet). In our design, there exist both linear and non-linear propagation steps, when processing each user or item node, and our gating module chooses one of them, which results in a hybrid model of the linear and non-linear GCN-based collaborative filtering (CF). The proposed model yields the best accuracy in three public benchmark datasets. Moreover, we classify users/items into the following three classes depending on our gating modules' selections: Full-Non-Linearity (FNL), Partial-Non-Linearity (PNL), and Full-Linearity (FL). We found that there exist strong correlations between nodes' centrality and their class membership, i.e., important user/item nodes exhibit more preferences towards the non-linearity during the propagation steps. To our knowledge, we are the first who design a hybrid method and report the correlation between the graph centrality and the linearity/non-linearity of nodes. All HMLET codes and datasets are available at:


page 1

page 2

page 3

page 4


Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach

Graph Convolutional Networks (GCNs) are state-of-the-art graph based rep...

Contrastive Collaborative Filtering for Cold-Start Item Recommendation

The cold-start problem is a long-standing challenge in recommender syste...

FusionDeepMF: A Dual Embedding based Deep Fusion Model for Recommendation

Traditional Collaborative Filtering (CF) based methods are applied to un...

Dissecting the Diffusion Process in Linear Graph Convolutional Networks

Graph Convolutional Networks (GCNs) have attracted more and more attenti...

Graph-less Collaborative Filtering

Graph neural networks (GNNs) have shown the power in representation lear...

Determination of Bayesian optimal warranty length under Type-II unified hybrid censoring scheme

Determination of an appropriate warranty length for the lifetime of the ...

LT-OCF: Learnable-Time ODE-based Collaborative Filtering

Collaborative filtering (CF) is a long-standing problem of recommender s...

Please sign up or login with your details

Forgot password? Click here to reset