Sparling: Learning Latent Representations With Extremely Sparse Activations
Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: machine learning, sparsity, interpretability, optimization
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: We introduce Sparling, an extreme activation sparsity layer and optimization algorithm that, when used in the middle of a neural network trained purely end-to-end, can recover the ground-truth intermediate features.
Abstract: Real-world processes often contain intermediate state that can be modeled as an extremely sparse tensor. We introduce Sparling, a technique that allows you to learn models with intermediate layers that match this state from only end-to-end labeled examples (i.e., no supervision on the intermediate state). Sparling uses a new kind of informational bottleneck that enforces levels of activation sparsity unachievable using other techniques. We find that extreme sparsity is necessary to achieve good intermediate state modeling. On our synthetic DigitCircle domain as well as the LaTeXOCR and AudioMNISTSequence domains, we are able to precisely localize the intermediate states up to feature permutation with $>90\%$ accuracy, even though we only train end-to-end.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 6189
Loading