AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

MHCN: A Hyperbolic Neural Network Model for Multi-view Hierarchical Clustering

Fangfei Lin, Bing Bai, Yiwen Guo, Hao Chen, Yazhou Ren, Zenglin Xu

ICCV 2023 · Learning theory and algorithms › Clustering · approach: Incomplete multi-view clustering · 14 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
one-stage hyperbolic multi-view training instead of two-stage CMHHCMHCN · MNIST-USPS, BDGP, Caltech, COIL-20, BBCSport, Multi-FashionDendrogram Purity: 94.49% -> 99.22% on MNIST-USPS; 53.50% -> 78.93% on BBCSportImproved
add multi-view alignment loss (ablation)MHCN · MNIST-USPSDendrogram Purity: 41.29% -> 99.22%Improved
add hyperbolic uniformity loss (ablation)MHCN · MNIST-USPSDendrogram Purity: 19.42% -> 99.22%Improved
add reconstruction loss (ablation)MHCN · seven multi-view datasetsDendrogram Purity: 99.07% -> 99.22% on MNIST-USPS; 75.17% -> 77.14% on CaltechImproved
use hyperbolic autoencoders instead of Euclidean autoencoders (ablation)MHCN · BDGPDendrogram Purity: 52.47% -> 96.22%Improved
use hyperbolic autoencoders instead of Euclidean autoencoders (ablation)MHCN · CaltechDendrogram Purity: 32.50% -> 77.14%Improved
increase weight of hyperbolic uniformity loss from 0 to 1 (ablation)MHCN · MNIST-USPS (2D Poincare ball)tree balance (qualitative)Improved
set alpha to 0 so alignment loss is dropped (ablation)MHCN · seven datasetsDendrogram PurityHurt
tune temperatures tau_align and tau_uni near 1.0 (ablation)MHCN · seven datasetsDendrogram PurityMixed
use mini-batch one-stage MHCN instead of agglomerative HACMHCN · NR-MNISTrunning time (s): 1823.43s (HAC-Single) -> 900.92sImproved
apply MHCN inductively to unseen dataMHCN · NR-MNISTDendrogram Purity: 98.71% -> 96.54%No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy