PAPER 13

Geometric Algebra Transformers

Johann Brehmer (Qualcomm AI Research)
Pim de Haan (Qualcomm AI Research)
Sönke Behrends (Qualcomm AI Research)
Taco Cohen (formerly Qualcomm AI Research)

NeurIPS 2023

Summary

Geometric algebra transformers (GATr) is a novel data-efficient architecture model to improve robots’ perception of their environment. GATr considers geometric structures of the physical environment through geometric algebra representations and equivariance. It has the scalability and expressivity of transformers. By embedding various kinds of geometric data into a single geometric algebra, GATr can process more geometric data types, making it suitable for a wide range of applications without requiring modifications to the network architecture.

Citation

@inproceedings{brehmer2023geometric, title = {Geometric Algebra Transformer}, author = {Brehmer, Johann and de Haan, Pim and Behrends, S{\"o}nke and Cohen, Taco}, booktitle = {Advances in Neural Information Processing Systems}, year = {2023}, volume = {37}, eprint = {2305.18415}, url = {https://arxiv.org/abs/2305.18415}, }

Results

We tested our method on several tasks, including robotic block stacking. In the graph above, our method outperforms all previous methods with 1% of the training data. As we scale the number of items, our method continues to outperform. GATr scales to tens of thousands of tokens, outperforming the geometric deep learning baselines.

Looking for more papers with code?

* Qualcomm AI Research is an initiative of Qualcomm Technologies, Inc.

 

Qualcomm relentlessly innovates to deliver intelligent computing everywhere, helping the world tackle some of its most important challenges. Our leading-edge AI, high performance, low-power computing, and unrivaled connectivity deliver proven solutions that transform major industries. At Qualcomm, we are engineering human progress.

Stay connected

Get the latest Qualcomm and industry information delivered to your inbox.

Subscribe
Manage your subscription
Also of Interest

© Qualcomm Technologies, Inc. and/or its affiliated companies.

Snapdragon and Qualcomm branded products are products of Qualcomm Technologies, Inc. and/or its subsidiaries. Qualcomm patented technologies are licensed by Qualcomm Incorporated.

Note: Certain services and materials may require you to accept additional terms and conditions before accessing or using those items.

References to "Qualcomm" may mean Qualcomm Incorporated, or subsidiaries or business units within the Qualcomm corporate structure, as applicable.

Qualcomm Incorporated includes our licensing business, QTL, and the vast majority of our patent portfolio. Qualcomm Technologies, Inc., a subsidiary of Qualcomm Incorporated, operates, along with its subsidiaries, substantially all of our engineering, research and development functions, and substantially all of our products and services businesses, including our QCT semiconductor business.

Materials that are as of a specific date, including but not limited to press releases, presentations, blog posts and webcasts, may have been superseded by subsequent events or disclosures.

Nothing in these materials is an offer to sell or license any of the services or materials referenced herein.