Keep your distance: learning dispersed embeddings on $\mathbb{S}_d$
- URL: http://arxiv.org/abs/2502.08231v1
- Date: Wed, 12 Feb 2025 09:20:08 GMT
- Title: Keep your distance: learning dispersed embeddings on $\mathbb{S}_d$
- Authors: Evgeniia Tokarchuk, Hua Chang Bakker, Vlad Niculae,
- Abstract summary: In representation learning we typically deal with a large number of features in high-dimensional space.
In this work, we give an overview of existing methods, making new connections and highlighting similarities.
We propose an online variant of the celebrated Lloyd's algorithm, of K-Means fame, as an effective alternative regularizer for dispersion on generic domains.
- Score: 9.708595749421022
- License:
- Abstract: Learning well-separated features in high-dimensional spaces, such as text or image embeddings, is crucial for many machine learning applications. Achieving such separation can be effectively accomplished through the dispersion of embeddings, where unrelated vectors are pushed apart as much as possible. By constraining features to be on a hypersphere, we can connect dispersion to well-studied problems in mathematics and physics, where optimal solutions are known for limited low-dimensional cases. However, in representation learning we typically deal with a large number of features in high-dimensional space, and moreover, dispersion is usually traded off with some other task-oriented training objective, making existing theoretical and numerical solutions inapplicable. Therefore, it is common to rely on gradient-based methods to encourage dispersion, usually by minimizing some function of the pairwise distances. In this work, we first give an overview of existing methods from disconnected literature, making new connections and highlighting similarities. Next, we introduce some new angles. We propose to reinterpret pairwise dispersion using a maximum mean discrepancy (MMD) motivation. We then propose an online variant of the celebrated Lloyd's algorithm, of K-Means fame, as an effective alternative regularizer for dispersion on generic domains. Finally, we derive a novel dispersion method that directly exploits properties of the hypersphere. Our experiments show the importance of dispersion in image classification and natural language processing tasks, and how algorithms exhibit different trade-offs in different regimes.
Related papers
- Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning [50.84938730450622]
We propose a trajectory-based method TV score, which uses trajectory volatility for OOD detection in mathematical reasoning.
Our method outperforms all traditional algorithms on GLMs under mathematical reasoning scenarios.
Our method can be extended to more applications with high-density features in output spaces, such as multiple-choice questions.
arXiv Detail & Related papers (2024-05-22T22:22:25Z) - Scaling Riemannian Diffusion Models [68.52820280448991]
We show that our method enables us to scale to high dimensional tasks on nontrivial manifold.
We model QCD densities on $SU(n)$ lattices and contrastively learned embeddings on high dimensional hyperspheres.
arXiv Detail & Related papers (2023-10-30T21:27:53Z) - Solving High-Dimensional PDEs with Latent Spectral Models [74.1011309005488]
We present Latent Spectral Models (LSM) toward an efficient and precise solver for high-dimensional PDEs.
Inspired by classical spectral methods in numerical analysis, we design a neural spectral block to solve PDEs in the latent space.
LSM achieves consistent state-of-the-art and yields a relative gain of 11.5% averaged on seven benchmarks.
arXiv Detail & Related papers (2023-01-30T04:58:40Z) - Message Passing Neural PDE Solvers [60.77761603258397]
We build a neural message passing solver, replacing allally designed components in the graph with backprop-optimized neural function approximators.
We show that neural message passing solvers representationally contain some classical methods, such as finite differences, finite volumes, and WENO schemes.
We validate our method on various fluid-like flow problems, demonstrating fast, stable, and accurate performance across different domain topologies, equation parameters, discretizations, etc., in 1D and 2D.
arXiv Detail & Related papers (2022-02-07T17:47:46Z) - High-dimensional separability for one- and few-shot learning [58.8599521537]
This work is driven by a practical question, corrections of Artificial Intelligence (AI) errors.
Special external devices, correctors, are developed. They should provide quick and non-iterative system fix without modification of a legacy AI system.
New multi-correctors of AI systems are presented and illustrated with examples of predicting errors and learning new classes of objects by a deep convolutional neural network.
arXiv Detail & Related papers (2021-06-28T14:58:14Z) - Rectangular Flows for Manifold Learning [38.63646804834534]
Normalizing flows are invertible neural networks with tractable change-of-volume terms.
Data of interest is typically assumed to live in some (often unknown) low-dimensional manifold embedded in high-dimensional ambient space.
We propose two methods to tractably the gradient of this term with respect to the parameters of the model.
arXiv Detail & Related papers (2021-06-02T18:30:39Z) - Adversarial Multi-task Learning Enhanced Physics-informed Neural
Networks for Solving Partial Differential Equations [9.823102211212582]
We introduce the novel approach of employing multi-task learning techniques, the uncertainty-weighting loss and the gradients surgery, in the context of learning PDE solutions.
In the experiments, our proposed methods are found to be effective and reduce the error on the unseen data points as compared to the previous approaches.
arXiv Detail & Related papers (2021-04-29T13:17:46Z) - Neural Operator: Graph Kernel Network for Partial Differential Equations [57.90284928158383]
This work is to generalize neural networks so that they can learn mappings between infinite-dimensional spaces (operators)
We formulate approximation of the infinite-dimensional mapping by composing nonlinear activation functions and a class of integral operators.
Experiments confirm that the proposed graph kernel network does have the desired properties and show competitive performance compared to the state of the art solvers.
arXiv Detail & Related papers (2020-03-07T01:56:20Z) - Solving inverse-PDE problems with physics-aware neural networks [0.0]
We propose a novel framework to find unknown fields in the context of inverse problems for partial differential equations.
We blend the high expressibility of deep neural networks as universal function estimators with the accuracy and reliability of existing numerical algorithms.
arXiv Detail & Related papers (2020-01-10T18:46:50Z)
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.