arXiv research

New framework improves reliability of learned representations by modeling uncertainty and structural constraints.

Study local structure of knot group representations into SL(n,C).

Unified framework for representation and causal structure learning using exchangeable data.

The paper proposes a deep learning technique for structured and composable representations.

New autoencoder learns structured representations without regularization.

Transformer learns graph structure better with subgraph info.

Introduces holed cone structures to generalize cone structures on 3-manifolds.

A fundamental problem in applying machine learning techniques for chemical problems is to find suitable representations for molecular and crystal structures. While the structure representations based on atom connectivities are prevalent for molecules, two-dimensional descriptors are not suitable for describing molecula…

Proposes FSM-IRL to learn invariant network representations considering feature and structural shifts.

Central to all machine learning algorithms is data representation. For multi-agent systems, selecting a representation which adequately captures the interactions among agents is challenging due to the latent group structure which tends to vary depending on context. However, in multi-agent systems with strong group stru…

We consider the relationship between hyperbolic cone-manifold structures on surfaces, and algebraic representations of the fundamental group into a group of isometries. A hyperbolic cone-manifold structure on a surface, with all interior cone angles being integer multiples of $2π$, determines a holonomy representation …

Structural identity is a concept of symmetry in which network nodes are identified according to the network structure and their relationship to other nodes. Structural identity has been studied in theory and practice over the past decades, but only recently has it been addressed with representational learning technique…

This work provides the first unifying theoretical framework for node (positional) embeddings and structural graph representations, bridging methods like matrix factorization and graph neural networks. Using invariant theory, we show that the relationship between structural representations and node embeddings is analogo…

We prove that a polar orthogonal representation of a real reductive algebraic group has the same closed orbits as the isotropy representation of a pseudo-Riemannian symmetric space. We also develop a partial structural theory of polar orthogonal representations of real reductive algebraic groups which slightly generali…

node2coords learns interpretable graph node representations robust to graph perturbations.

Let $K(X)$ denote the set of projective structures on a compact Riemann surface $X$ whose holonomy representations are discrete. We will show that each component of the interior of $K(X)$ is holomorphically equivalent to a complex submanifold of the product of Teichmüller spaces and the holonomy representation of every…

Many machine learning algorithms represent input data with vector embeddings or discrete codes. When inputs exhibit compositional structure (e.g. objects built from parts or procedures from subroutines), it is natural to ask whether this compositional structure is reflected in the the inputs' learned representations. W…

Learning disentangled representations is a key step towards effectively discovering and modelling the underlying structure of environments. In the natural sciences, physics has found great success by describing the universe in terms of symmetry preserving transformations. Inspired by this formalism, we propose a framew…

Anosov deformations created for surfaces with specific properties.

CRATE-MAE learns structured representations from unlabeled data.

Study quandle modules over geometric quandles and their relation to Lie-Yamaguti representations.

Graph Information Bottleneck (GIB) optimizes graph representations for robustness against adversarial attacks.

TRUST improves structure learning with tractable uncertainty.

Agent learns diverse hierarchical structures in unknown environments.

The paper proposes a method to learn structured representations from unlabeled data using mutual information maximization.

The paper studies geometric representations of submanifolds using complex-valued functions.

For each oriented surface $Σ$ of genus $g$ we study a limit of quantum representations of the mapping class group arising in TQFT derived from the Kauffman bracket. We determine that these representations converge in the Fell topology to the representation of the mapping class group on $\boH(Σ)$, the space of regular f…

We consider the relationship between hyperbolic cone-manifold structures on surfaces, and algebraic representations of the fundamental group into a group of isometries. A hyperbolic cone-manifold structure on a surface, with all interior cone angles being integer multiples of $2π$, determines a holonomy representation …

Auto-encoders have emerged as a successful framework for unsupervised learning. However, conventional auto-encoders are incapable of utilizing explicit relations in structured data. To take advantage of relations in graph-structured data, several graph auto-encoders have recently been proposed, but they neglect to reco…

Study on projective structures linked to Hitchin representations.

Improves representation learning for individual treatment effect estimation.

Representation learning is a fundamental but challenging problem, especially when the distribution of data is unknown. We propose a new representation learning method, termed Structure Transfer Machine (STM), which enables feature learning process to converge at the representation expectation in a probabilistic way. We…

The paper explores how AI trading agents' similar information representation can cause financial market instability.

This paper clarifies vine copula structures using graph and matrix representations.

New method learns unbiased treatment representations from structured high-dimensional data.

The paper classifies fiber structures of discontinuity domains for Anosov representations.

Performing machine learning on structured data is complicated by the fact that such data does not have vectorial form. Therefore, multiple approaches have emerged to construct vectorial representations of structured data, from kernel and distance approaches to recurrent, recursive, and convolutional neural networks. Re…

We propose a novel method of introducing structure into existing machine learning techniques by developing structure-based similarity and distance measures. To learn structural information, low-dimensional structure of the data is captured by solving a non-linear, low-rank representation problem. We show that this low-…

We describe recent links between two topics: geometric structures on manifolds in the sense of Ehresmann and Thurston, and dynamics "at infinity" for representations of discrete groups into Lie groups.

We study primitive stable representations of free groups into higher rank semisimple Lie groups and their properties. Let $Σ$ be a compact, connected, orientable surface (possibly with boundary) of negative Euler characteristic. We first verify the $σ_{mod}$-regularity for convex projective structures and positive repr…

Researchers present and compare different representations of dissipative Hamiltonian DAE systems.

iREPA shows spatial structure, not global semantic, drives generation performance in REPA.

Clustering is a fundamental task in data analysis. Recently, deep clustering, which derives inspiration primarily from deep learning approaches, achieves state-of-the-art performance and has attracted considerable attention. Current deep clustering methods usually boost the clustering results by means of the powerful r…

We introduce and study a new class of representations of surface groups into Lie groups of Hermitian type, called weakly maximal representations. They are defined in terms of invariants in bounded cohomology and extend considerably the scope of maximal representations. We prove that weakly maximal representations are d…

The paper explores how AI systems use information geometry to encode semantic structure.

Study identifies specialist representations from generalist models without parametric constraints.

Study angle structures on 3-manifolds, linking to representation theory.

Recently S. Merkulov established a new link between differential geometry and homological algebra by giving descriptions of several differential geometric structures in terms of algebraic operads and props. In particular he described Nijenhuis structures as corresponding to representations of the cobar construction on …