Dark Side of Modalities: Reinforced Multimodal Distillation for Multimodal Knowledge Graph Reasoning

TL;DR

This paper introduces a Reinforced Multimodal Distillation framework that leverages the hidden, non-target, and potentially misleading information in multimodal knowledge graphs to improve reasoning accuracy.

Contribution

It proposes a novel framework that distills dark knowledge from non-target entities and dynamically selects beneficial modalities, addressing limitations of previous static and single-target approaches.

Findings

Significant performance improvements on 5 MKGR datasets.

Effective exclusion of unhelpful modalities through reinforcement learning.

Enhanced utilization of subtle correlations in multimodal data.

Abstract

The multimodal knowledge graph reasoning (MKGR) task aims to predict the missing facts in the incomplete MKGs by leveraging auxiliary images and descriptions of entities. Existing approaches are trained with single-target objectives, which neglect the probabilistic correlations of entity labels, especially in non-target entities. Moreover, previous studies incorporate all modalities statically or adaptively, overlooking the negative impacts of irrelevant or misleading information in the incompetent modalities. To address these issues, we introduce a novel Reinforced Multimodal Distillation framework, exploiting the Dark Side of Modalities (DSoM) from two perspectives: (1) Dark knowledge from non-target entities: We propose to train a unimodal KGR model through logit distillation to mimic the multimodal soft labels provided by pre-trained multimodal teacher models. The multimodal soft labels could provide rich supervision signals with subtle correlations among both target and non-target entities from multiple perspectives. We further decouple logits into neighbor entities and non-neighbor entities to divide into two types of correlations. (2) Dark side in unhelpful modalities: To exclude the adverse effects of unhelpful modalities, we introduce a reinforced teacher combination mechanism that dynamically selects the optimal set of multimodal teachers for each triple. The agent is trained to maximize the rewards, which are only assigned to the beneficial multimodal combination strategies for the student model. Comprehensive experiments demonstrate the effectiveness of DSoM framework on 5 MKGR datasets. Codes are available at github.com/OreOZhao/DSoM.