Task-specific Geometric Sensitive Hashing (T-GSH)

This repository is the official implementation of Task-specific Geometric Sensitive Hashing.

Abstract

Geometric Sensitive Hashing functions, a family of Local Sensitive Hashing functions, are neural network models that learn class-specific manifold geometry in supervised learning. However, given a set of supervised learning tasks, understanding the manifold geometries that can represent each task and the kinds of relationships between the tasks based on them has received little attention. We explore a formalization of this question by considering a generative process where each task is associated with a high-dimensional manifold, which can be done in brain-like models with neuromodulatory systems. Following this formulation, we define Task-specific Geometric Sensitive Hashing and show that a randomly weighted neural network with a neuromodulation system can realize this function.

Experiments

• RotationMNIST: See FlyNet - RotationMNIST.ipynb
• ShiftMNIST: Code will be posted soon :)
• AugmentMNIST: Code will be posted soon :)

Acknowledgement

Our work is based on:

• For Manifold Learning, Deep Neural Networks can be Locality Sensitive Hash Functions
• Learning to Modulate Random Weights: Neuromodulation-inspired Neural Networks For Efficient Continual Learning

Reference

You can cite our work:

@inproceedings{hong2023randomly,
 author = {Jinyung Hong and Theodore P. Pavlic},
 booktitle = {UniReps:  the First Workshop on Unifying Representations in Neural Models},
 title = {Randomly Weighted Neuromodulation in Neural Networks Facilitates Learning of Manifolds Common Across Tasks},
 url = {https://openreview.net/forum?id=EHvgtRcrix},
 year = {2023}
}