The paper introduces QUEST, a method for uncertain knowledge graph completion that adds no trainable parameters to the standard pipeline. QUEST first initializes entity embeddings using the smallest non‑trivial eigenvectors of the confidence‑weighted graph Laplacian, thereby preserving community and hub structure before training. It then applies an unbiased mini‑batch Dirichlet energy regularizer to enforce early‑stage structural consistency, leading to improved confidence and link prediction on most metric‑dataset pairs and eliminating instability spikes on dense graphs.
arXiv:2606. 16509v1 Announce Type: new Abstract: Link prediction in knowledge graphs fundamentally depends on the quality of learned embeddings for entities and relations.
arXiv:2606. 03365v1 Announce Type: new Abstract: Embedding models (KGEMs) constitute the main link prediction approach to complete knowledge graphs.
arXiv:2610.06974v1 Announce Type: new Abstract: Knowledge graph embedding (KGE) methods represent entities and predicates in continuous vector spaces to infer missing knowledge. Despite strong benchm...
PEARL is a new framework for inductive knowledge graph completion that treats relational paths as context-conditioned reasoning signals. It builds a query‑specific contextual subgraph from the query entities’ neighborhoods and uses a large language model‑guided retriever to select semantically relevant paths. By constructing a bipartite interaction graph over paths, contextual entities, and a global subgraph representation, and applying a dual‑view contrastive objective, PEARL adapts path embeddings to local and global structural evidence, achieving the best average Hits@10 on WN18RR, FB15k‑237, and NELL‑995.
arXiv:2607. 10159v1 Announce Type: new Abstract: In real-world multimodal web scenarios, graph-structured data often arrives in a streaming manner, making graph continual learning a crucial paradigm for continuously modeling such evolving structures.
arXiv:2610.02517v1 Announce Type: new Abstract: Graph-structured data plays a pivotal role in modeling complex relationships. However, real-world graphs are often incomplete due to data collection an...
arXiv:2607. 03154v1 Announce Type: cross Abstract: Multi-domain knowledge graph completion (MKGC) aims to improve missing triple prediction in a target KG by transferring knowledge from other support KGs.
arXiv:2510. 09711v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have recently emerged as a powerful paradigm for Knowledge Graph Completion (KGC), offering strong reasoning and generalization capabilities beyond traditional embedding-based approaches.
The paper introduces G^2MLP, a graph‑free MLP trained via distillation from a GNN teacher while preserving the teacher’s graph‑induced geometry. It identifies two spectral failure modes—underfit on sparse graphs and overfit on dense graphs—caused by neglecting geometry during distillation. By using Ollivier‑Ricci curvature to guide supervision between prediction‑level and representation‑level alignment, G^2MLP improves node‑classification performance and reduces the teacher‑student rank gap across benchmarks.
BLADE is a variational model for knowledge graph completion that separates latent truth from graph recording and uses distilled offline language‑model judgments as a frozen teacher regularizer. The model provides calibrated probabilities and epistemic uncertainty through posterior samples, while the teacher is only an optional triage factor during inference. Across five benchmarks, BLADE matches ranking performance and significantly reduces expected calibration error, improving ECE, Brier score, and NLL over several baselines, and shows strong performance under controlled missingness and leakage stress tests.
arXiv:2606. 17667v1 Announce Type: cross Abstract: In recent years, the rapid development of foundation models and graph pre-training technologies has spurred increasing interest in constructing a universal pre-trained graph model or Graph Foundation Model (GFM).
The paper introduces GONE, a benchmark for evaluating knowledge unlearning in large language models using structured knowledge graphs, and presents Neighborhood-Expanded Distribution Shaping (NEDS), a framework that leverages graph connectivity to separate forgotten facts from their semantic neighborhood. GONE disentangles direct fact removal, reasoning-based leakage, and catastrophic forgetting, while NEDS achieves high unlearning efficacy and locality on LLaMA-3-8B and Mistral-7B. The dataset is publicly available on Hugging Face.