Unsupervised Learning of Equivariant Structure from Sequences
- URL: http://arxiv.org/abs/2210.05972v1
- Date: Wed, 12 Oct 2022 07:29:18 GMT
- Title: Unsupervised Learning of Equivariant Structure from Sequences
- Authors: Takeru Miyato, Masanori Koyama, Kenji Fukumizu
- Abstract summary: We present an unsupervised framework to learn the symmetry from the time sequence of length at least three.
We will demonstrate that, with our framework, the hidden disentangled structure of the dataset naturally emerges as a by-product.
- Score: 30.974508897223124
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In this study, we present meta-sequential prediction (MSP), an unsupervised
framework to learn the symmetry from the time sequence of length at least
three. Our method leverages the stationary property (e.g. constant velocity,
constant acceleration) of the time sequence to learn the underlying equivariant
structure of the dataset by simply training the encoder-decoder model to be
able to predict the future observations. We will demonstrate that, with our
framework, the hidden disentangled structure of the dataset naturally emerges
as a by-product by applying simultaneous block-diagonalization to the
transition operators in the latent space, the procedure which is commonly used
in representation theory to decompose the feature-space based on the type of
response to group actions. We will showcase our method from both empirical and
theoretical perspectives. Our result suggests that finding a simple structured
relation and learning a model with extrapolation capability are two sides of
the same coin. The code is available at
https://github.com/takerum/meta_sequential_prediction.
Related papers
- Unsupervised Representation Learning from Sparse Transformation Analysis [79.94858534887801]
We propose to learn representations from sequence data by factorizing the transformations of the latent variables into sparse components.
Input data are first encoded as distributions of latent activations and subsequently transformed using a probability flow model.
arXiv Detail & Related papers (2024-10-07T23:53:25Z) - Skeleton2vec: A Self-supervised Learning Framework with Contextualized
Target Representations for Skeleton Sequence [56.092059713922744]
We show that using high-level contextualized features as prediction targets can achieve superior performance.
Specifically, we propose Skeleton2vec, a simple and efficient self-supervised 3D action representation learning framework.
Our proposed Skeleton2vec outperforms previous methods and achieves state-of-the-art results.
arXiv Detail & Related papers (2024-01-01T12:08:35Z) - Intensity Profile Projection: A Framework for Continuous-Time
Representation Learning for Dynamic Networks [50.2033914945157]
We present a representation learning framework, Intensity Profile Projection, for continuous-time dynamic network data.
The framework consists of three stages: estimating pairwise intensity functions, learning a projection which minimises a notion of intensity reconstruction error.
Moreoever, we develop estimation theory providing tight control on the error of any estimated trajectory, indicating that the representations could even be used in quite noise-sensitive follow-on analyses.
arXiv Detail & Related papers (2023-06-09T15:38:25Z) - Disentanglement via Latent Quantization [60.37109712033694]
In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space.
We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
arXiv Detail & Related papers (2023-05-28T06:30:29Z) - Exploring Predictive States via Cantor Embeddings and Wasserstein
Distance [0.0]
We show how Wasserstein distances may be used to detect predictive equivalences in symbolic data.
We show that exploratory data analysis using the resulting geometry provides insight into the temporal structure of processes.
arXiv Detail & Related papers (2022-06-09T00:09:47Z) - Parameter Decoupling Strategy for Semi-supervised 3D Left Atrium
Segmentation [0.0]
We present a novel semi-supervised segmentation model based on parameter decoupling strategy to encourage consistent predictions from diverse views.
Our method has achieved a competitive result over the state-of-the-art semisupervised methods on the Atrial Challenge dataset.
arXiv Detail & Related papers (2021-09-20T14:51:42Z) - Topographic VAEs learn Equivariant Capsules [84.33745072274942]
We introduce the Topographic VAE: a novel method for efficiently training deep generative models with topographically organized latent variables.
We show that such a model indeed learns to organize its activations according to salient characteristics such as digit class, width, and style on MNIST.
We demonstrate approximate equivariance to complex transformations, expanding upon the capabilities of existing group equivariant neural networks.
arXiv Detail & Related papers (2021-09-03T09:25:57Z) - Predicting Temporal Sets with Deep Neural Networks [50.53727580527024]
We propose an integrated solution based on the deep neural networks for temporal sets prediction.
A unique perspective is to learn element relationship by constructing set-level co-occurrence graph.
We design an attention-based module to adaptively learn the temporal dependency of elements and sets.
arXiv Detail & Related papers (2020-06-20T03:29:02Z) - Towards Novel Insights in Lattice Field Theory with Explainable Machine
Learning [1.5854412882298003]
We propose representation learning in combination with interpretability methods as a framework for the identification of observables.
The approach is put to work in the context of a scalar Yukawa model in (2+1)d.
Based on our results, we argue that due to its broad applicability, attribution methods such as LRP could prove a useful and versatile tool in our search for new physical insights.
arXiv Detail & Related papers (2020-03-03T13:56:58Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.