# Emotion Collider: Dual Hyperbolic Mirror Manifolds for Sentiment Recovery via Anti Emotion Reflection

arXiv: https://arxiv.org/abs/2602.16161 · HTML: https://mlsanity.com/paper/2602.16161/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 54 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Builds on (most cited first, 27 of 27)

- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [SMIL: Multimodal Learning with Severely Missing Modality](https://mlsanity.com/paper/2103.05677/) (2021)
- [Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models](https://mlsanity.com/paper/2305.12827/) (2023)
- [Memory Fusion Network for Multi-view Sequential Learning](https://mlsanity.com/paper/1802.00927/) (2018)
- [Hyperbolic Vision Transformers: Combining Improvements in Metric Learning](https://mlsanity.com/paper/2203.10833/) (2022)
- [Deep Multimodal Learning with Missing Modality: A Survey](https://mlsanity.com/paper/2409.07825/) (2024)
- [GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation](https://mlsanity.com/paper/2203.02177/) (2022)
- [UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition](https://mlsanity.com/paper/2211.11256/) (2022)
- [Probing BERT in Hyperbolic Spaces](https://mlsanity.com/paper/2104.03869/) (2021)
- [Hypformer: Exploring Efficient Transformer Fully in Hyperbolic Space](https://mlsanity.com/paper/2407.01290/) (2024)
- [Hybrid Contrastive Learning of Tri-Modal Representation for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2109.01797/) (2021)
- [Disentanglement of Correlated Factors via Hausdorff Factorized Support](https://mlsanity.com/paper/2210.07347/) (2022)
- [Towards Robust Multimodal Sentiment Analysis with Incomplete Data](https://mlsanity.com/paper/2409.20012/) (2024)
- [DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis](https://mlsanity.com/paper/2412.12225/) (2024)
- [Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentation](https://mlsanity.com/paper/2304.10756/) (2023)
- [Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes](https://mlsanity.com/paper/2310.07216/) (2023)
- [Analyzing Modality Robustness in Multimodal Sentiment Analysis](https://mlsanity.com/paper/2205.15465/) (2022)
- [Hyperbolic Diffusion Embedding and Distance for Hierarchical Representation Learning](https://mlsanity.com/paper/2305.18962/) (2023)
- [Generalization Error Bound for Hyperbolic Ordinal Embedding](https://mlsanity.com/paper/2105.10475/) (2021)
- [A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech Recognition](https://mlsanity.com/paper/2403.04245/) (2024)
- [Label-Aware Hyperbolic Embeddings for Fine-grained Emotion Classification](https://mlsanity.com/paper/2306.14822/) (2023)
- [Generalizing Knowledge Graph Embedding with Universal Orthogonal Parameterization](https://mlsanity.com/paper/2405.08540/) (2024)
- [Learning Robust Self-attention Features for Speech Emotion Recognition with Label-adaptive Mixup](https://mlsanity.com/paper/2305.06273/) (2023)
- [HyDiscGAN: A Hybrid Distributed cGAN for Audio-Visual Privacy Preservation in Multimodal Sentiment Analysis](https://mlsanity.com/paper/2404.11938/) (2024)
- [Dealing with All-stage Missing Modality: Towards A Universal Model with Robust Reconstruction and Personalization](https://mlsanity.com/paper/2406.01987/) (2024)
- [Conformally Natural Families of Probability Distributions on Hyperbolic Disc with a View on Geometric Deep Learning](https://mlsanity.com/paper/2407.16733/) (2024)
- [Improving Speech Emotion Recognition with Unsupervised Speaking Style Transfer](https://mlsanity.com/paper/2211.08843/) (2022)

## Built on by (most cited first, 2 of 2)

- [HyPASE: Hyperbolic Geometry for Parameter-Efficient Speech Emotion Fine-Tuning Framework for Large Audio-Language Models](https://mlsanity.com/paper/2608.04351/) (2026)
- [GeoMER: A Joint Euclidean-Hyperbolic Geometry Framework for Multimodal Emotion Recognition](https://mlsanity.com/paper/2610.18587/) (2026)

## Abstract (arXiv)

Emotional expression underpins natural communication and effective human-computer interaction. We present Emotion Collider (EC-Net), a hyperbolic hypergraph framework for multimodal emotion and sentiment modeling. EC-Net represents modality hierarchies using Poincare-ball embeddings and performs fusion through a hypergraph mechanism that passes messages bidirectionally between nodes and hyperedges. To sharpen class separation, contrastive learning is formulated in hyperbolic space with decoupled radial and angular objectives. High-order semantic relations across time steps and modalities are preserved via adaptive hyperedge construction. Empirical results on standard multimodal emotion benchmarks show that EC-Net produces robust, semantically coherent representations and consistently improves accuracy, particularly when modalities are partially available or contaminated by noise. These findings indicate that explicit hierarchical geometry combined with hypergraph fusion is effective for resilient multimodal affect understanding.