Systems and methods for neural network based recommender models

A system for training a neural network based model, the system comprising:

• a memory that stores the neural network based model and a plurality of processor executable instructions;
• a communication interface that receives a training dataset comprising a plurality of training samples;
• and
• one or more hardware processors that read and execute the plurality of processor-executable instructions from the memory to perform operations comprising:
• encoding, by the neural network based model, at least a subset of the plurality of training samples into representations in a feature space;
• determining, for a given query, a positive sample from the training dataset based on a relationship in the feature space between the given query and the positive sample;
• selecting, for the given query, one or more negative samples from the training dataset that are within a reconfigurable distance in the feature space to the positive sample;
• computing a loss based on the positive sample and the one or more negative samples;
• training the neural network based model based on the loss;
• and
• iteratively performing the determining, selecting, computing, and training across a plurality of iterations by:
• decreasing the reconfigurable distance across a first portion of the plurality of iterations, wherein a rate of the decreasing is computed based on an estimate of an amount of noise in the training dataset, and
• increasing the reconfigurable distance across a second portion of the plurality of iterations.

A non-transitory machine-readable medium comprising a plurality of machine-executable instructions which, when executed by one or more processors, are adapted to cause the one or more processors to perform operations comprising:

• receiving, via a communication interface, a training dataset comprising a plurality of training samples;
• encoding, by a neural network based model, at least a subset of the plurality of training samples into representations in a feature space;
• determining, for a given query, a positive sample from the training dataset based on a relationship in the feature space between the given query and the positive sample;
• selecting, for the given query, one or more negative samples from the training dataset that are within a reconfigurable distance in the feature space to the positive sample;
• computing a loss based on the positive sample and the one or more negative samples;
• training the neural network based model based on the loss;
• and
• iteratively performing the determining, selecting, computing, and training across a plurality of iterations by:
• decreasing the reconfigurable distance across a first portion of the plurality of iterations, wherein a rate of the decreasing is computed based on an estimate of an amount of noise in the training dataset, and
• increasing the reconfigurable distance across a second portion of the plurality of iterations.