paper-with-me

홈 › Papers

Pooling by Sliced-Wasserstein Embedding

2021-12-01 · NeurIPS 2021 12 · Navid Naderializadeh, Joseph Comer, Reed Andrews, Heiko Hoffmann, Soheil Kolouri

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.

📄 PDF Abstract BibTeX

Code (1)

navid-naderi/pswe pytorch

Tasks

Graph Learningimage-classificationImage Classificationobject-detectionObject DetectionRepresentation LearningVideo Recognition

Similar Papers 제목 키워드 기반

Fourier Sliced-Wasserstein Embedding for Multisets and Measures

2025-04-03 · Tal Amir, Nadav Dym

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

2021-12-11 · Yuzhe Lu, Xinran Liu, Andrea Soltoggio, Soheil Kolouri

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 …

Retrieval

Fourier Sliced-Wasserstein Embedding for Multisets and Measures

2024-05-26 · Tal Amir, Nadav Dym

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

2021-03-05 · Navid Naderializadeh, Soheil Kolouri, Joseph F. Comer, Reed W. Andrews 외

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 Learning

Wasserstein Hypergraph Neural Network

2025-06-11 · Iulia Duta, Pietro Liò

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