DeConFuse: A Deep Convolutional Transform based Unsupervised Fusion Framework

Pooja Gupta (1) , Jyoti Maggu (1) , Angshul Majumdar (2, 1) , Emilie Chouzenoux (3) , Giovanni Chierchia (4, 5)

1 IIIT-Delhi - Indraprastha Institute of Information Technology [New Delhi]
2 TCS - Tata Consultancy Services Research
3 OPIS - OPtimisation Imagerie et Santé
4 ESIEE Paris
5 LIGM - Laboratoire d'Informatique Gaspard-Monge

This work proposes an unsupervised fusion framework based on deep convolutional transform learning. The great learning ability of convolutional filters for data analysis is well acknowledged. The success of convolutive features owes to convolutional neural network (CNN). However , CNN cannot perform learning tasks in an unsupervised fashion. In a recent work, we show that such shortcoming can be addressed by adopting a convolutional transform learning (CTL) approach, where con-volutional filters are learnt in an unsupervised fashion. The present paper aims at (i) proposing a deep version of CTL ; (ii) proposing an unsu-pervised fusion formulation taking advantage of the proposed deep CTL representation ; (iii) developing a mathematically sounded optimization strategy for performing the learning task. We apply the proposed technique , named DeConFuse, on the problem of stock forecasting and trading. Comparison with state-of-the-art methods (based on CNN and long short-term memory network) shows the superiority of our method for performing a reliable feature extraction.

Mots clés: stock trading; financial forecasting; information fusion; convolution; deep learning

Domaines: Traitement du signal et de l'image [eess.SP]

Pooja Gupta, Jyoti Maggu, Angshul Majumdar, Emilie Chouzenoux, Giovanni Chierchia. DeConFuse: A Deep Convolutional Transform based Unsupervised Fusion Framework. 2020. ⟨hal-02461768⟩