Learning curvature-aware multimodal representations with bicomplex embeddings

Thanh Le Vy Cao Duong-Khang Au Trong-Nghia Pham Bac Le

Sep 2026 · Data mining and knowledge discovery · Vol 40 · 0 citations · 27 references

View source

Similar papers

Conference Open access Sep 2026

AdaGeM: Adaptive Geometric Learning on Manifolds for Hyper-Relational Knowledge Graphs

An adaptive geometric hypergraph encoder that projects entities into a product manifold and design a topology-aware gating mechanism to dynamically select optimal geometric spaces for each entity, and a role-aware Transformer equipped with role-specific projections and micro-structural bias injection to refine embeddin...

Ke-Jia Chen, Yu-Zhe Hu, Yu Ni et al. · Proceedings of the Thirty-Fi... · 0 citations

Open access Aug 2026

SynAlign: cross-curvature synergistic Euclidean–hyperbolic entity alignment for knowledge graphs

Entity alignment is a fundamental step for knowledge graph (KG) integration, yet the complex and heterogeneous structures of real-world KGs make accurate alignment particularly challenging. KG entity alignment faces two main challenges. First, representations learned in a single Euclidean or hyperbolic space struggle t...

Teng Fu, Gang Zhou, Chao Zhang · Journal of King Saud Univers... · 0 citations

#machine learning Preprint Sep 2026

ICE: Task-Aligned Clifford Latent Fields for Multimodal Graph Foundation Models

This work introduces ICE (Interaction-aware Clifford Encoder), a multimodal graph foundation model built on a node-indexed Clifford latent field that ranks first in all 30 reported supervised and few-shot comparisons.

Xun-Kai Li, Xu Wang, Yin-Lin Zhu et al. · 0 citations

#graph neural networks Preprint Aug 2026

ReCoG: Reciprocal Co-Evolution for Multimodal Graph Learning

ReCoG (Reciprocal Co-Evolution for Multimodal Graph Learning) is proposed, a new learning paradigm that tightly couples graph structure learning and multimodal representation learning through end-to-end reciprocal interaction and yields greater expressiveness than decoupled or two-stage formulations.

Rui Xue, Tianfu Wu · 0 citations

#machine learning Preprint Sep 2026

Binding Multiple Modalities via Multimodal Wasserstein Barycenter

BaryBind is presented, which aims to transport the specific modality towards the Wasserstein barycenter (WB) optimized across all modalities and introduces a volumetric alignment objective to establish a unified semantic space around the WB embedding.

Xiao-Le Tang, Jia-Yi Xu, Xiang Gu et al. · 2 citations

Aug 2026

Semantic manifold-aware cross-modal similarity learning.

A Semantic Manifold-Aware Similarity Learning (SMSL) framework, where the term "semantic manifold" is used in an operational sense to denote a topology-aware organization of textual semantic units induced from token/entity interactions, rather than a strict low-dimensional differentiable manifold.

Li-Qi Zhu, De-Zhi Han, Chong-Qing Chen · Neural Networks · 0 citations