MLCTR: A Fast Scalable Coupled Tensor Completion Based on Multi-Layer Non-Linear Matrix Factorization

TL;DR

This paper introduces MLCTR, a scalable neural network-based tensor completion method that effectively models non-linear relationships, reduces overfitting, and improves missing data imputation in complex datasets.

Contribution

The paper proposes a novel multi-layer neural network architecture for tensor completion that integrates low-rank matrix factorizations, non-linear transfer functions, and bypass connections for enhanced performance.

Findings

Outperforms existing methods in embedding learning accuracy.

Efficiently imputes missing values in financial datasets.

Demonstrates robustness against overfitting in tensor completion.

Abstract

Firms earning prediction plays a vital role in investment decisions, dividends expectation, and share price. It often involves multiple tensor-compatible datasets with non-linear multi-way relationships, spatiotemporal structures, and different levels of sparsity. Current non-linear tensor completion algorithms tend to learn noisy embedding and incur overfitting. This paper focuses on the embedding learning aspect of the tensor completion problem and proposes a new multi-layer neural network architecture for tensor factorization and completion (MLCTR). The network architecture entails multiple advantages: a series of low-rank matrix factorizations (MF) building blocks to minimize overfitting, interleaved transfer functions in each layer for non-linearity, and by-pass connections to reduce the gradient diminishing problem and increase the depths of neural networks. Furthermore, the model employs Stochastic Gradient Descent(SGD) based optimization for fast convergence in training. Our algorithm is highly efficient for imputing missing values in the EPS data. Experiments confirm that our strategy of incorporating non-linearity in factor matrices demonstrates impressive performance in embedding learning and end-to-end tensor models, and outperforms approaches with non-linearity in the phase of reconstructing tensors from factor matrices.