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

TL;DR

Emotion Collider (EC-Net) introduces a hyperbolic hypergraph framework for multimodal emotion modeling, leveraging Poincare-ball embeddings and contrastive learning to improve robustness and accuracy in emotion recognition.

Contribution

The paper proposes a novel hyperbolic hypergraph approach with contrastive learning for multimodal emotion analysis, enhancing semantic coherence and resilience to noise.

Findings

EC-Net improves emotion recognition accuracy on standard benchmarks.

The framework maintains semantic coherence even with noisy or missing modalities.

Hyperbolic geometry and hypergraph fusion enhance multimodal affect understanding.

Abstract

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.