# Silence and Noise: Resolving Suppression and Overvaluation in Multimodal Entity Alignment

arXiv: https://arxiv.org/abs/2610.16106 · HTML: https://mlsanity.com/paper/2610.16106/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 41 references that are in the map.
- First posted on arXiv 12 Oct 2026.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Cross-lingual Entity Alignment via Joint Attribute-Preserving Embedding](https://mlsanity.com/paper/1708.05045/) (2017)
- [MMKG: Multi-Modal Knowledge Graphs](https://mlsanity.com/paper/1903.05485/) (2019)
- [Deep Multimodal Learning with Missing Modality: A Survey](https://mlsanity.com/paper/2409.07825/) (2024)
- [Visual Pivoting for (Unsupervised) Entity Alignment](https://mlsanity.com/paper/2009.13603/) (2020)
- [Multi-modal Contrastive Representation Learning for Entity Alignment](https://mlsanity.com/paper/2209.00891/) (2022)
- [MEAformer: Multi-modal Entity Alignment Transformer for Meta Modality Hybrid](https://mlsanity.com/paper/2212.14454/) (2022)
- [KBLRN : End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features](https://mlsanity.com/paper/1709.04676/) (2017)
- [Attribute-Consistent Knowledge Graph Representation Learning for Multi-Modal Entity Alignment](https://mlsanity.com/paper/2304.01563/) (2023)
- [Rethinking Uncertainly Missing and Ambiguous Visual Modality in Multi-Modal Entity Alignment](https://mlsanity.com/paper/2307.16210/) (2023)
- [Dissimilarity-based Sparse Subset Selection](https://mlsanity.com/paper/1407.6810/) (2014)
- [ActiveEA: Active Learning for Neural Entity Alignment](https://mlsanity.com/paper/2110.06474/) (2021)
- [Revisit and Outstrip Entity Alignment: A Perspective of Generative Models](https://mlsanity.com/paper/2305.14651/) (2023)
- [Deep Active Alignment of Knowledge Graph Entities and Schemata](https://mlsanity.com/paper/2304.04389/) (2023)
- [Multi-Modal Knowledge Graph Transformer Framework for Multi-Modal Entity Alignment](https://mlsanity.com/paper/2310.06365/) (2023)
- [Active Learning for Entity Alignment](https://mlsanity.com/paper/2001.08943/) (2020)
- [Multimodal Negative Learning](https://mlsanity.com/paper/2510.20877/) (2025)

## Abstract (arXiv)

Multimodal entity alignment (MMEA) is fundamental to integrating heterogeneous knowledge graphs (KGs), yet existing paradigms remain critically vulnerable to incomplete modalities and cross-graph structural asymmetries. This paper exposes a fundamental oversight in current MMEA research: treating feature missingness and topological discrepancies as isolated preprocessing or denoising challenges, which overlooks their destructive coupling during multimodal fusion. We systematically formulate and evaluate two newly identified failure modes: 1) Detail Missing (DM)-induced overvaluation, where the absence of local modality details causes models to overemphasize uninformative, blurred representations; and 2) Context Imbalance (CI)-induced suppression, where topological discrepancies across KGs allow dense structural contexts to overwhelm weaker but highly discriminative modal signals, triggering high-level semantic drift. To break this cycle of degradation, we introduce ALMEA, a generative and calibration framework that establishes a bidirectional feedback loop between low-level feature reconstruction and high-level latent space alignment. Specifically, Cross-Modality Imputation (CMI) synthesizes missing modality details to mitigate overvaluation, while Latent Semantic Calibration (LSC) aligns cross-graph joint embeddings to suppress topology-driven semantic drift. Under sparse supervision, we develop Controlled Iterative Selection (CIS) to adaptively acquire representative and diverse pseudo-labeled pairs, optimizing latent calibration under constrained budgets. Extensive evaluations on standard benchmarks demonstrate that ALMEA consistently outperforms state-of-the-art baselines. At a 20% supervision rate, ALMEA yields substantial absolute improvements of up to 5.20% in MRR and 6.40% in Hits@1, maintaining robust gains across higher supervision thresholds.