HyperFusion: Hierarchical Multimodal Ensemble Learning for Social Media Popularity Prediction

TL;DR

HyperFusion is a hierarchical ensemble framework that integrates visual, textual, and metadata features to improve social media popularity prediction, demonstrating competitive results and winning third place in a challenge.

Contribution

It introduces a novel three-tier fusion architecture with hierarchical ensemble strategies and a two-stage training process for social media popularity prediction.

Findings

Achieved third place in SMP Challenge 2025 (Image Track)

Demonstrated competitive performance on the SMP dataset

Proposed novel cross-modal similarity measures and clustering features

Abstract

Social media popularity prediction plays a crucial role in content optimization, marketing strategies, and user engagement enhancement across digital platforms. However, predicting post popularity remains challenging due to the complex interplay between visual, textual, temporal, and user behavioral factors. This paper presents HyperFusion, a hierarchical multimodal ensemble learning framework for social media popularity prediction. Our approach employs a three-tier fusion architecture that progressively integrates features across abstraction levels: visual representations from CLIP encoders, textual embeddings from transformer models, and temporal-spatial metadata with user characteristics. The framework implements a hierarchical ensemble strategy combining CatBoost, TabNet, and custom multi-layer perceptrons. To address limited labeled data, we propose a two-stage training methodology with pseudo-labeling and iterative refinement. We introduce novel cross-modal similarity measures and hierarchical clustering features that capture inter-modal dependencies. Experimental results demonstrate that HyperFusion achieves competitive performance on the SMP challenge dataset. Our team achieved third place in the SMP Challenge 2025 (Image Track). The source code is available at https://anonymous.4open.science/r/SMPDImage.