MORTIS: Towards Multi-Modal and Multi-Scale Federated Knowledge Graph Completion

doi:10.1109/TKDE.2026.3689321

MORTIS: Towards Multi-Modal and Multi-Scale Federated Knowledge Graph Completion

2026-04-30

0

PRE

AI

DOI：10.1109/TKDE.2026.3689321

Original

Original request for help

Save

Abstract

En 中文

Federated knowledge graph completion (FedKGC) enables collaborative discovery of new knowledge across distributed clients with privacy-preserved consideration, supported by a global server for local knowledge aggregation. Existing FedKGC methods focus on idealized scenarios, neglecting the multi-modal information and multi-scale data distribution in real-world knowledge graphs (KGs). We contend that these complex scenarios introduce new difficulties while persisting limitations remain, notably in three perspectives: the private sharing of multi-modal knowledge, dependence on an omniscient server, and misalignment between locally and globally optimal models. To address these issues, we propose MORTIS, a unified FedKGC framework featuring novel local KGC models and global aggregation strategies. Multi-modal codebooks (MUCO) are the central stars on both the client and server sides. MORTIS employs MUCOs to build fine-grained, hierarchical local KGC models. An auxiliary self-supervised sequence denoising loss enhances entity representations. Furthermore, MORTIS implements partial low-rank adaptation on the MUCOs, facilitating efficient and theoretically convergent multi-modal knowledge aggregation. Comprehensive experiments on public benchmark indicate the effectiveness, robustness, reasonability, and efficiency of MORTIS in complex heterogeneous FedKGC scenarios.

Keywords:

Multi-modal knowledge graph

federated knowledge graph completion

modality tokenization

fine-grained multi-modal fusion

low-rank adaption

MORTIS: Towards Multi-Modal and Multi-Scale Federated Knowledge Graph Completion

Abstract

Journal

Organization