Unsupervised Learning of Group Invariant and Equivariant Representations
Authors: Robin Winter, Marco Bertolini, Tuan Le, Frank Noe, Djork-Arné Clevert
NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We test the validity and the robustness of our approach in a variety of experiments with diverse data types employing different network architectures.In this section we present differnt experiments for the various groups discussed in Section 3. |
| Researcher Affiliation | Collaboration | Robin Winter Bayer AG Freie Universität Berlin robin.winter@bayer.com Marco Bertolini Bayer AG marco.bertolini@bayer.com Tuan Le Bayer AG Freie Universität Berlin tuan.le2@bayer.com Frank Noé Freie Universität Berlin Microsoft Research frank.noe@fu-berlin.de Djork-Arné Clevert Bayer AG djork-arne.clevert@bayer.com |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Source code for the different implementations available at https://github.com/jrwnter/giae. |
| Open Datasets | Yes | In the first experiment, we train an SO(2)-invariant autoencoder on the original (non-rotated) MNIST dataset and validate the trained model on the rotated MNIST dataset (ref. mni) which consists of randomly rotated versions of the original MNIST dataset.Rotated MNIST. https://sites.google.com/a/lisa.iro.umontreal.ca/public_ static_twiki/variations-on-the-mnist-digits. [Online; accessed 05-January-2021].We showcase our learning framework on real-world data by autoencoding the atom types and geometries of small molecules from the QM9 database Ramakrishnan et al. (2014). |
| Dataset Splits | Yes | We randomly sampled 1.000.000 different sets for training and 100.000 for the final evaluation with N = 20, 30, 40, 100, respectively, removing all permutation equivariant sets (i.e., there are no two sets that are the same up to a permutation). The classifier based on our rotation-invariant embeddings achieved an accuracy of 0.81 while the classifier based on the non-invariant embeddings achieved an accuracy of only 0.63. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU or CPU models, memory) used for running its experiments. |
| Software Dependencies | No | The paper mentions using specific network architectures like 'SO(2)-Steerable Convolutional Neural Networks' and '3D Steerable CNNs', but does not provide specific version numbers for any software dependencies or libraries. |
| Experiment Setup | Yes | For more details about the network architecture and training, we refer to Appendix B. We use a batch size of 128 and train the model for 50 epochs using the Adam optimizer with a learning rate 10^-3. |