Pooling by Sliced-Wasserstein Embedding
Learning representations from sets has become increasingly important with many applications in point cloud processing, graph learning, image/video recognition, and object detection. We introduce a geometrically-interpretable and generic pooling mechanism for aggregating a set of features into a fixed-dimensional representation. In particular, we treat elements of a set as samples from a probability distribution and propose an end-to-end trainable Euclidean embedding for sliced-Wasserstein distance to learn from set-structured data effectively. We evaluate our proposed pooling method on a wide variety of set-structured data, including point-cloud, graph, and image classification tasks, and demonstrate that our proposed method provides superior performance over existing set representation learning approaches. Our code is available at https://github.com/navid-naderi/PSWE.
Code (1)
Tasks
Graph Learningimage-classificationImage Classificationobject-detectionObject DetectionRepresentation LearningVideo RecognitionSimilar Papers 제목 키워드 기반
Fourier Sliced-Wasserstein Embedding for Multisets and Measures
We present the Fourier Sliced-Wasserstein (FSW) embedding - a novel method to embed multisets and measures over $\mathbb{R}^d$ into Euclidean space. Our proposed embedding approximately preserves the sliced Wasserstein d…
SLOSH: Set LOcality Sensitive Hashing via Sliced-Wasserstein Embeddings
Learning from set-structured data is an essential problem with many applications in machine learning and computer vision. This paper focuses on non-parametric and data-independent learning from set-structured data using …
RetrievalFourier Sliced-Wasserstein Embedding for Multisets and Measures
We present the $\textit{Fourier Sliced Wasserstein (FSW) embedding}\unicode{x2014}$a novel method to embed multisets and measures over $\mathbb{R}^d$ into Euclidean space. Our proposed embedding approximately preserves t…
Set Representation Learning with Generalized Sliced-Wasserstein Embeddings
An increasing number of machine learning tasks deal with learning representations from set-structured data. Solutions to these problems involve the composition of permutation-equivariant modules (e.g., self-attention, or…
Representation LearningWasserstein Hypergraph Neural Network
The ability to model relational information using machine learning has driven advancements across various domains, from medicine to social science. While graph representation learning has become mainstream over the past …
Graph Representation LearningNode ClassificationRepresentation Learning