BTW: A Non-Parametric Variance Stabilization Framework for Multimodal Model Integration

• URL: http://arxiv.org/abs/2508.18551v1
• Date: Mon, 25 Aug 2025 23:00:38 GMT
• Title: BTW: A Non-Parametric Variance Stabilization Framework for Multimodal Model Integration
• Authors: Jun Hou, Le Wang, Xuan Wang,
• Abstract summary: We propose Beyond Two-modality Weighting (BTW) to dynamically adjust modality importance during training.<n>BTW computes per-example KL weights by measuring the divergence between each unimodal and the current multimodal prediction.<n>Our method significantly improves regression performance and multiclass classification accuracy.
• Score: 20.600001069987318
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mixture-of-Experts (MoE) models have become increasingly powerful in multimodal learning by enabling modular specialization across modalities. However, their effectiveness remains unclear when additional modalities introduce more noise than complementary information. Existing approaches, such as the Partial Information Decomposition, struggle to scale beyond two modalities and lack the resolution needed for instance-level control. We propose Beyond Two-modality Weighting (BTW), a bi-level, non-parametric weighting framework that combines instance-level Kullback-Leibler (KL) divergence and modality-level mutual information (MI) to dynamically adjust modality importance during training. Our method does not require additional parameters and can be applied to an arbitrary number of modalities. Specifically, BTW computes per-example KL weights by measuring the divergence between each unimodal and the current multimodal prediction, and modality-wide MI weights by estimating global alignment between unimodal and multimodal outputs. Extensive experiments on sentiment regression and clinical classification demonstrate that our method significantly improves regression performance and multiclass classification accuracy.

Related papers

• Mixup Helps Understanding Multimodal Video Better [12.281180208753021]
  Multimodal models are prone to overfitting strong modalities, which can dominate learning and suppress the contributions of weaker ones.<n>We propose Multimodal Mixup (MM), which applies the Mixup strategy at the aggregated multimodal feature level to mitigate overfitting.<n>We also introduce Balanced Multimodal Mixup (B-MM), which dynamically adjusts the mixing ratios for each modality based on their relative contributions to the learning objective.
  arXiv  Detail & Related papers  (2025-10-13T03:53:25Z)
• A Robust Incomplete Multimodal Low-Rank Adaptation Approach for Emotion Recognition [17.332141776831513]
  Multimodal Emotion Recognition (MER) often encounters incomplete multimodality in practical applications.<n>We propose a unimodal decoupled dynamic low-rank adaptation method based on modality combinations, named MCULoRA.
  arXiv  Detail & Related papers  (2025-07-15T11:15:35Z)
• FindRec: Stein-Guided Entropic Flow for Multi-Modal Sequential Recommendation [57.577843653775]
  We propose textbfFindRec (textbfFlexible unified textbfinformation textbfdisentanglement for multi-modal sequential textbfRecommendation)<n>A Stein kernel-based Integrated Information Coordination Module (IICM) theoretically guarantees distribution consistency between multimodal features and ID streams.<n>A cross-modal expert routing mechanism that adaptively filters and combines multimodal features based on their contextual relevance.
  arXiv  Detail & Related papers  (2025-07-07T04:09:45Z)
• MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings [75.0617088717528]
  MoCa is a framework for transforming pre-trained VLM backbones into effective bidirectional embedding models.<n>MoCa consistently improves performance across MMEB and ViDoRe-v2 benchmarks, achieving new state-of-the-art results.
  arXiv  Detail & Related papers  (2025-06-29T06:41:00Z)
• Modality Equilibrium Matters: Minor-Modality-Aware Adaptive Alternating for Cross-Modal Memory Enhancement [13.424541949553964]
  We propose a Shapley-guided alternating training framework that adaptively prioritizes minor modalities to balance and thus enhance the fusion.<n>We evaluate the performance in both balance and accuracy across four multimodal benchmark datasets, where our method achieves state-of-the-art (SOTA) results.
  arXiv  Detail & Related papers  (2025-05-26T02:02:57Z)
• DynCIM: Dynamic Curriculum for Imbalanced Multimodal Learning [15.524342129628957]
  DynCIM is a novel dynamic curriculum learning framework designed to quantify the inherent imbalances from both sample and modality perspectives.<n>DynCIM employs a sample-level curriculum to dynamically assess each sample's difficulty according to prediction deviation, consistency, and stability.<n>A modality-level curriculum measures modality contributions from global and local.
  arXiv  Detail & Related papers  (2025-03-09T05:30:15Z)
• On-the-fly Modulation for Balanced Multimodal Learning [53.616094855778954]
  Multimodal learning is expected to boost model performance by integrating information from different modalities. The widely-used joint training strategy leads to imbalanced and under-optimized uni-modal representations. We propose On-the-fly Prediction Modulation (OPM) and On-the-fly Gradient Modulation (OGM) strategies to modulate the optimization of each modality.
  arXiv  Detail & Related papers  (2024-10-15T13:15:50Z)
• When Parameter-efficient Tuning Meets General-purpose Vision-language Models [65.19127815275307]
  PETAL revolutionizes the training process by requiring only 0.5% of the total parameters, achieved through a unique mode approximation technique. Our experiments reveal that PETAL not only outperforms current state-of-the-art methods in most scenarios but also surpasses full fine-tuning models in effectiveness.
  arXiv  Detail & Related papers  (2023-12-16T17:13:08Z)
• Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding [62.70450216120704]
  Unsupervised pre-training has shown great success in skeleton-based action understanding. We propose a Unified Multimodal Unsupervised Representation Learning framework, called UmURL. UmURL exploits an efficient early-fusion strategy to jointly encode the multi-modal features in a single-stream manner.
  arXiv  Detail & Related papers  (2023-11-06T13:56:57Z)
• Improving Discriminative Multi-Modal Learning with Large-Scale Pre-Trained Models [51.5543321122664]
  This paper investigates how to better leverage large-scale pre-trained uni-modal models to enhance discriminative multi-modal learning. We introduce Multi-Modal Low-Rank Adaptation learning (MMLoRA)
  arXiv  Detail & Related papers  (2023-10-08T15:01:54Z)
• Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis [96.46952672172021]
  Bi-Bimodal Fusion Network (BBFN) is a novel end-to-end network that performs fusion on pairwise modality representations. Model takes two bimodal pairs as input due to known information imbalance among modalities.
  arXiv  Detail & Related papers  (2021-07-28T23:33:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.