RESCAL model trained with a relation prediction objective on top of the 1vsAll loss

**Kaleido-BERT**(CVPR2021) is the pioneering work that focus on solving PTM in e-commerce field. It achieves SOTA performances compared with many models published in general domain.

Kaleido-BERT

RESCAL-RP

Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations

A **Deep Belief Network (DBN)** is a multi-layer generative graphical model. DBNs have bi-directional connections ([RBM](https://paperswithcode.com/method/restricted-boltzmann-machine)-type connections) on the top layer while the bottom layers only have top-down connections. They are trained using layerwise pre-training. Pre-training occurs by training the network component by component bottom up: treating the first two layers as an RBM and training, then treating the second layer and third layer as another RBM and training for those parameters.

Source: [Origins of Deep Learning](https://arxiv.org/pdf/1702.07800.pdf)

Image Source: [Wikipedia](https://en.wikipedia.org/wiki/Deep_belief_network)

Source	Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com

Viet-Anh on Software

What is: RESCAL with Relation Prediction?

Viet-Anh on Software