An interpretable latent variable model for attribute applicability in the Amazon catalogue

11/30/2017
by   Tammo Rukat, et al.
0

Learning attribute applicability of products in the Amazon catalog (e.g., predicting that a shoe should have a value for size, but not for battery-type at scale is a challenge. The need for an interpretable model is contingent on (1) the lack of ground truth training data, (2) the need to utilise prior information about the underlying latent space and (3) the ability to understand the quality of predictions on new, unseen data. To this end, we develop the MaxMachine, a probabilistic latent variable model that learns distributed binary representations, associated to sets of features that are likely to co-occur in the data. Layers of MaxMachines can be stacked such that higher layers encode more abstract information. Any set of variables can be clamped to encode prior information. We develop fast sampling based posterior inference. Preliminary results show that the model improves over the baseline in 17 out of 19 product groups and provides qualitatively reasonable predictions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/02/2023

Shared Latent Space by Both Languages in Non-Autoregressive Neural Machine Translation

Latent variable modeling in non-autoregressive neural machine translatio...
research
10/21/2015

Creating Scalable and Interactive Web Applications Using High Performance Latent Variable Models

In this project we outline a modularized, scalable system for comparing ...
research
06/30/2016

Unsupervised Learning with Imbalanced Data via Structure Consolidation Latent Variable Model

Unsupervised learning on imbalanced data is challenging because, when gi...
research
12/09/2019

No Representation without Transformation

We propose to extend Latent Variable Models with a simple idea: learn to...
research
12/12/2017

GibbsNet: Iterative Adversarial Inference for Deep Graphical Models

Directed latent variable models that formulate the joint distribution as...
research
01/20/2022

A Latent-Variable Model for Intrinsic Probing

The success of pre-trained contextualized representations has prompted r...
research
10/12/2021

A bridge between features and evidence for binary attribute-driven perfect privacy

Attribute-driven privacy aims to conceal a single user's attribute, cont...

Please sign up or login with your details

Forgot password? Click here to reset