📹 Video: https://youtu.be/uzx2gxOhn14
Papers are hard to write. Survey papers are just that much harder. From the authors' perspective, challenges include the responsibility to not erase out important work being done by (sometimes) adversarially aligned research groups, finding the right semantic clustering to sub-categorize individual contributions, controlling for the verbosity and length of the final paper, ensuring an optimal mixing of personal opinion and the innate narratives in the paper(s) being cited, version controlling, ease of updating, and also the aesthetics of presentation. From the reader's viewpoint, challenges include ease of reading, single-snapshot summarizability, portability, and being given the agency to edit or fork their own copies.
Taking cues from the emergence of the cheat-sheet culture in machine learning and the virtues of living editable documentation and version control, we propose an interactive and live SVG format based methodology that we term SPICE: Survey Papers as Interactive Cheat-sheet Embedding. We cover the technical details behind constructing SPICEs and present an example gallery covering hot button' areas in machine learning such as Out of distribution detection, the All you need' histrionics and Transformer architectures.
Portal for interactive SPICEs is here
@inproceedings{prabhu2020spices,
title={SPICES: Survey Papers As Interactive Cheatsheet Embeddings},
author={Prabhu, Uday Vinay and
McAteer, Matthew and Teehan, Ryan and Whaley, John },
booktitle={Rethinking ML Papers - ICLR 2021 Workshop},
howpublished = {\url{https://openreview.net/pdf?id=1sysg9hi3KS}},
month = {April},
year = {2021},
note = {(Accessed on 04/03/2021)}
year={2021}
}
| SPICE | TL-DR |
|---|---|
| 1. SPICE for Out of distribution landscape | Literature sorrounding Out-of-distribution landscape in recent ML literature |
| 2. SPICE for X-is all you need | What do ML'ers mean when they say, X is all you need! |
| 3. SPICE for X-former architectures | Re-renditioning of Tay et al's X-former architecture survey |
