paper-with-me

Papers

Hypformer: Exploring Efficient Hyperbolic Transformer Fully in Hyperbolic Space

2024-07-01 · Menglin Yang, Harshit Verma, Delvin Ce Zhang, Jiahong Liu, Irwin King, Rex Ying

Hyperbolic geometry have shown significant potential in modeling complex structured data, particularly those with underlying tree-like and hierarchical structures. Despite the impressive performance of various hyperbolic neural networks across numerous domains, research on adapting the Transformer to hyperbolic space remains limited. Previous attempts have mainly focused on modifying self-attention modules in the Transformer. However, these efforts have fallen short of developing a complete hyperbolic Transformer. This stems primarily from: (i) the absence of well-defined modules in hyperbolic space, including linear transformation layers, LayerNorm layers, activation functions, dropout operations, etc. (ii) the quadratic time complexity of the existing hyperbolic self-attention module w.r.t the number of input tokens, which hinders its scalability. To address these challenges, we propose, Hypformer, a novel hyperbolic Transformer based on the Lorentz model of hyperbolic geometry. In Hypformer, we introduce two foundational blocks that define the essential modules of the Transformer in hyperbolic space. Furthermore, we develop a linear self-attention mechanism in hyperbolic space, enabling hyperbolic Transformer to process billion-scale graph data and long-sequence inputs for the first time. Our experimental results confirm the effectiveness and efficiency of Hypformer across various datasets, demonstrating its potential as an effective and scalable solution for large-scale data representation and large models.

📄 PDF Abstract BibTeX arXiv:2407.01290

Code (1)

Graph-and-Geometric-Learning/hyperbolic-transformer 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

HyperCore: The Core Framework for Building Hyperbolic Foundation Models with Comprehensive Modules

2025-04-11 · Neil He, Menglin Yang, Rex Ying

Hyperbolic neural networks have emerged as a powerful tool for modeling hierarchical data across diverse modalities. Recent studies show that token distributions in foundation models exhibit scale-free properties, sugges…

RAG

Fully Hyperbolic Neural Networks

2021-05-31 · ACL 2022 5 · Weize Chen, Xu Han, Yankai Lin, Hexu Zhao 외

Hyperbolic neural networks have shown great potential for modeling complex data. However, existing hyperbolic networks are not completely hyperbolic, as they encode features in a hyperbolic space yet formalize most of th…

Fully Hyperbolic Neural Networks

2021-10-16 · ACL ARR October 2021 10 · Anonymous

Hyperbolic neural networks have shown great potential for modeling complex data. However, existing hyperbolic networks are not completely hyperbolic, as they encode features in the hyperbolic space yet formalize most of …

Fully Hyperbolic Convolutional Neural Networks for Computer Vision

2023-03-28 · Ahmad Bdeir, Kristian Schwethelm, Niels Landwehr

Real-world visual data exhibit intrinsic hierarchical structures that can be represented effectively in hyperbolic spaces. Hyperbolic neural networks (HNNs) are a promising approach for learning feature representations i…

Image ClassificationImage Generation

HexFormer: Hyperbolic Vision Transformer with Exponential Map Aggregation

2026-01-27 · Haya Alyoussef, Ahmad Bdeir, Diego Coello de Portugal Mecke, Tom Hanika 외 arxiv

Data across modalities such as images, text, and graphs often contains hierarchical and relational structures, which are challenging to model within Euclidean geometry. Hyperbolic geometry provides a natural framework fo…

Image Classification