SAGE: Scale-Aware Gradual Evolution for Continual Knowledge Graph Embedding

• URL: http://arxiv.org/abs/2508.11347v1
• Date: Fri, 15 Aug 2025 09:23:23 GMT
• Title: SAGE: Scale-Aware Gradual Evolution for Continual Knowledge Graph Embedding
• Abstract summary: We propose SAGE, a scale-aware gradual evolution framework for knowledge graph embedding.<n>SAGE consistently outperforms existing baselines, with a notable improvement of 1.38% in MRR, 1.25% in H@1 and 1.6% in H@10.<n>Experiments comparing SAGE with methods using fixed embedding dimensions show that SAGE achieves optimal performance on every snapshot.
• Score: 14.115513111911673
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Traditional knowledge graph (KG) embedding methods aim to represent entities and relations in a low-dimensional space, primarily focusing on static graphs. However, real-world KGs are dynamically evolving with the constant addition of entities, relations and facts. To address such dynamic nature of KGs, several continual knowledge graph embedding (CKGE) methods have been developed to efficiently update KG embeddings to accommodate new facts while maintaining learned knowledge. As KGs grow at different rates and scales in real-world scenarios, existing CKGE methods often fail to consider the varying scales of updates and lack systematic evaluation throughout the entire update process. In this paper, we propose SAGE, a scale-aware gradual evolution framework for CKGE. Specifically, SAGE firstly determine the embedding dimensions based on the update scales and expand the embedding space accordingly. The Dynamic Distillation mechanism is further employed to balance the preservation of learned knowledge and the incorporation of new facts. We conduct extensive experiments on seven benchmarks, and the results show that SAGE consistently outperforms existing baselines, with a notable improvement of 1.38% in MRR, 1.25% in H@1 and 1.6% in H@10. Furthermore, experiments comparing SAGE with methods using fixed embedding dimensions show that SAGE achieves optimal performance on every snapshot, demonstrating the importance of adaptive embedding dimensions in CKGE. The codes of SAGE are publicly available at: https://github.com/lyfxjtu/Dynamic-Embedding.

Related papers

• Revisiting Catastrophic Forgetting in Continual Knowledge Graph Embedding [2.422410293747519]
  Knowledge Graph Embeddings (KGEs) support a wide range of downstream tasks over Knowledge Graphs (KGs)<n>Current CKGE approaches address catastrophic forgetting primarily by limiting changes to existing embeddings.<n>When new entities are introduced, their embeddings can interfere with previously learned ones, causing the model to predict them in place of previously correct answers.
  arXiv  Detail & Related papers  (2026-04-21T12:26:56Z)
• Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams [78.9560820155271]
  We evaluate online adaptation over streaming, continually updating knowledge.<n> OAKS comprises two datasets: OAKS-BABI and OAKS-Novel.<n>Both state-of-the-art models and agentic memory systems fail to adapt robustly on OAKS.
  arXiv  Detail & Related papers  (2026-03-08T00:38:39Z)
• Towards Practical Large-scale Dynamical Heterogeneous Graph Embedding: Cold-start Resilient Recommendation [45.70605679051105]
  This paper introduces a practical, two-stage solution that balances deep graph representation with low-latency incremental updates.<n>Our framework combines HetSGFormer, a scalable graph transformer for static learning, with Incremental Locally Linear Embedding (ILLE), a lightweight, CPU-based algorithm for real-time updates.
  arXiv  Detail & Related papers  (2025-12-15T09:19:23Z)
• Learning to Evolve: Bayesian-Guided Continual Knowledge Graph Embedding [20.479556500981044]
  Key challenge facing continual knowledge graph embedding (CKGE) is that the model is prone to "catastrophic forgetting"<n>In order to effectively alleviate this problem, we propose a new CKGE model BAKE.
  arXiv  Detail & Related papers  (2025-08-04T13:46:33Z)
• Towards Improving Long-Tail Entity Predictions in Temporal Knowledge Graphs through Global Similarity and Weighted Sampling [53.11315884128402]
  Temporal Knowledge Graph (TKG) completion models traditionally assume access to the entire graph during training.<n>We present an incremental training framework specifically designed for TKGs, aiming to address entities that are either not observed during training or have sparse connections.<n>Our approach combines a model-agnostic enhancement layer with a weighted sampling strategy, that can be augmented to and improve any existing TKG completion method.
  arXiv  Detail & Related papers  (2025-07-25T06:02:48Z)
• KG-Infused RAG: Augmenting Corpus-Based RAG with External Knowledge Graphs [66.35046942874737]
  KG-Infused RAG is a framework that integrates KGs into RAG systems to implement spreading activation.<n> KG-Infused RAG retrieves KG facts, expands the query accordingly, and enhances generation by combining corpus passages with structured facts.
  arXiv  Detail & Related papers  (2025-06-11T09:20:02Z)
• STCKGE:Continual Knowledge Graph Embedding Based on Spatial Transformation [6.534658139904185]
  We propose STCKGE, a novel Continual Knowledge Graph Embedding framework based on spatial transformation.<n>In this framework, entity positions are jointly determined by base position vectors and offset vectors.<n>We show that STCKGE's strong performance in multi-hop relationship learning and prediction accuracy, with an average MRR improvement of 5.4%.
  arXiv  Detail & Related papers  (2025-03-11T08:54:03Z)
• GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion [52.026016846945424]
  We propose a new method called GLTW, which encodes the structural information of KGs and merges it with Large Language Models.<n>Specifically, we introduce an improved Graph Transformer (iGT) that effectively encodes subgraphs with both local and global structural information.<n>Also, we develop a subgraph-based multi-classification training objective, using all entities within KG as classification objects, to boost learning efficiency.
  arXiv  Detail & Related papers  (2025-02-17T06:02:59Z)
• Fast and Continual Knowledge Graph Embedding via Incremental LoRA [20.624310261539694]
  Continual Knowledge Graph Embedding aims to efficiently learn new knowledge and simultaneously preserve old knowledge. We propose a fast CKGE framework (model) incorporating an incremental low-rank adapter (mec) mechanism to efficiently acquire new knowledge. We conduct experiments on four public datasets and two new datasets with a larger initial scale.
  arXiv  Detail & Related papers  (2024-07-08T08:07:13Z)
• KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge [63.19837262782962]
  Knowledge Graph Embedding (KGE) techniques are crucial in learning compact representations of entities and relations within a knowledge graph. This study introduces KG-FIT, which builds a semantically coherent hierarchical structure of entity clusters. Experiments on the benchmark datasets FB15K-237, YAGO3-10, and PrimeKG demonstrate the superiority of KG-FIT over state-of-the-art pre-trained language model-based methods.
  arXiv  Detail & Related papers  (2024-05-26T03:04:26Z)
• Towards Continual Knowledge Graph Embedding via Incremental Distillation [12.556752486002356]
  Traditional knowledge graph embedding (KGE) methods typically require preserving the entire knowledge graph (KG) with significant training costs when new knowledge emerges. This paper proposes a competitive method for CKGE based on incremental distillation (IncDE), which considers the full use of the explicit graph structure in KGs.
  arXiv  Detail & Related papers  (2024-05-07T16:16:00Z)
• Lifelong Embedding Learning and Transfer for Growing Knowledge Graphs [22.88552158340435]
  Existing knowledge graph embedding models primarily focus on static KGs. New facts and previously unseen entities and relations continually emerge, necessitating an embedding model that can quickly learn and transfer new knowledge through growth. We consider knowledge transfer and retention of the learning on growing snapshots of a KG without having to learn embeddings from scratch. The proposed model includes a masked KG autoencoder for embedding learning and update, with an embedding transfer strategy to inject the learned knowledge into the new entity and relation embeddings, and an embedding regularization method to avoid catastrophic forgetting.
  arXiv  Detail & Related papers  (2022-11-29T00:43:44Z)
• Explainable Sparse Knowledge Graph Completion via High-order Graph Reasoning Network [111.67744771462873]
  This paper proposes a novel explainable model for sparse Knowledge Graphs (KGs) It combines high-order reasoning into a graph convolutional network, namely HoGRN. It can not only improve the generalization ability to mitigate the information insufficiency issue but also provide interpretability.
  arXiv  Detail & Related papers  (2022-07-14T10:16:56Z)
• Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning [59.004025528223025]
  Key to predict future facts is to thoroughly understand the historical facts. A TKG is actually a sequence of KGs corresponding to different timestamps. We propose a novel Recurrent Evolution network based on Graph Convolution Network (GCN)
  arXiv  Detail & Related papers  (2021-04-21T05:12:21Z)

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.