cs.LGAug 25, 2026

SNAP-KG: Streaming Node Assignment via Projection for Knowledge Graph Entity Integration

Authors: Jui-Chien Lin, Mohammad Mohammadi Amiri, Oshani Seneviratne

Organizations: Rensselaer Polytechnic Institute, Troy, NY 12180, USA

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Knowledge graph (KG) construction pipelines must continuously integrate newly arriving entities into a growing graph. Unlike inserting triples between existing nodes, a newly arriving entity has no graph connectivity: it emerges from the acquisition phase as a raw feature vector and must be assigned to a semantic community before entity resolution and link prediction can operate over a tractable candidate set. Existing multi-view graph clustering methods exploit multiple relation types as structural views, but are transductive: they assume a fixed graph and cannot assign unseen entities without retraining. We propose SNAP-KG (Streaming Node Assignment via Projection for Knowledge Graph Entity Integration), a framework supporting graph-structural multi-view relational clustering and inductive inference for streaming entities. SNAP-KG trains a projector to map a new entity directly to the learned embedding space using only raw features, enabling immediate cluster assignment without graph access or model retraining. Experiments on five benchmark multi-view graph datasets and a production-scale KG of 2.4 million nodes demonstrate multiple orders-of-magnitude inference speedups over retraining-based approaches and competitive clustering quality. As a candidate scoping mechanism for downstream tasks, SNAP-KG achieves 62-75% candidate search reduction on the five benchmark datasets and 97% on OGB-WikiKG2 for entity resolution and link prediction.

Figures & tables

Figure 1: SNAP-KG addresses the streaming entity integration sub-problem within Phase 2 (Knowledge Refinement) of the KG construction pipeline. A newly arriving entity carries only raw node features and no graph connectivity. SNAP-KG assigns it to an existing cluster via an inductive projector fϕf_{\phi} without retraining, enabling downstream entity resolution (ER) and link prediction (LP) to be scoped within the assigned cluster and reducing the candidate search space.
Figure 2: Overview of SNAP-KG framework. The projector network is trained to simulate the combined functionality of the view-specific GNNs and multi-view encoder, enabling efficient embedding generation for streaming nodes. For clarity, only two views are shown.
Figure 3: Overall ACC and F1 across successive batches on ACM, DBLP, YELP, and MAG. Solid: ACC; dashed: F1. SNAP-KG-Projector (green) closely tracks SNAP-KG-Retrain (red), while BMGC-Retrain (blue) and DEMM-Retrain (orange) require >> 65 s of retraining per batch on MAG.
More in this topic

KG Construction

Knowledge graph construction turns text, tables, images, and databases into structured entities and relationships that machines can query and reason over.

See all 195 papers

Explore similar work

CardsList
Sep 11, 2026

When Connected Does Not Mean Similar: Charting the Homophily Boundary of SNAP-KG for Streaming Entity Integration

SNAP-KG is a framework for assigning newly arriving entities to semantic communities in a growing knowledge graph (KG) using only their raw features, with no graph access and no retraining at inference time. It was evaluated on five multi-view benchmarks and a 2.4M-node OGB-WikiKG2 KG. In each of these datasets, at least one graph view is homophilous, meaning that connected nodes usually belong to the same class, and SNAP-KG performs well on all of them. This paper asks what happens outside that setting. We extend the evaluation to three heterophilous graphs (Texas, Wisconsin, Chameleon) and measure the edge homophily of every view. When no homophilous view is available, clustering quality drops sharply for both SNAP-KG and the transductive baselines used in its original evaluation. What decides this is the homophily of the relation, not the number of relations. Multi-view fusion still helps, but only when at least one homophilous relation provides a reliable foundation. The homophily assumption is therefore shared by the whole method family, not specific to SNAP-KG. We argue that heterophilous multi-view clustering is a separate research problem, outside the scope of this work. As future work, we outline how a heterophily-aware teacher could be distilled into SNAP-KG's projector to serve both homophilous and heterophilous KGs.

Jui-Chien Lin, Oshani Seneviratne

Rensselaer Polytechnic Institute, Troy, NY 12180, USA

Multi-View ClusteringGraph ClusteringKnowledge GraphsGraph Heterophily
AskPDF
Jun 15, 2026

Model Graph Inductive Learning for Knowledge Graph Completion

Link prediction in knowledge graphs fundamentally depends on the quality of learned embeddings for entities and relations. However, most existing methods derive these embeddings by aggregating only the local neighborhood of each entity, neglecting the global structure of the knowledge graph. This limited view prevents models from capturing higher-level structural patterns that are essential for accurate and generalizable link prediction. To address these limitations, we introduce Model Graph Inductive Learning (MGIL), a framework that constructs a model graph by clustering entities based on the similarity of their incoming and outgoing relational structures or their entity types. A GNN is then applied to this model graph to produce embeddings that capture the global view of the knowledge graph. These embeddings subsequently serve as high-quality initial features %embeddings for the original knowledge graph, replacing random initialization and leading to more stable and expressive representations. Extensive experiments on standard and recently proposed inductive benchmarks demonstrate that MGIL achieves state-of-the-art or highly competitive performance in inductive link prediction, highlighting its effectiveness across diverse graph settings.

Mohommad Esmaei Khani, Mahdieh Hasheminejad, Ali Taherkhani +1

Faculty of Mathematical Science Department of Computer Science, Yazd Unversity,, 100190, Iran. · Department of Mathematics, Institute for Advanced Studies in Basic Sciences (IASBS), 45137-66731, Iran. · Diagnostic and Research Institute of Human Genetics, Medizinische Universität Graz, Graz, 8010, Austria.

Graph Neural NetworksLink PredictionKG EmbeddingKG Completion
AskPDF
Aug 25, 2026

FedV-KGQA: Multi-Hop Question Answering over Vertically Partitioned Knowledge Graphs

Real-world data for knowledge graph question answering is often distributed across different organizations due to governance and data sovereignty constraints. While centralized systems exist, they cannot answer multi-hop questions when the required facts are split across vertically partitioned silos. In this paper, we propose FedV-KGQA, a framework for multi-hop reasoning over knowledge graphs in which organizations share entities but own disjoint sets of relations. Our approach combines local graph enrichment and knowledge graph embeddings to ensure raw triples and relation parameters never leave each silo, establishing a structural data boundary without requiring centralized graph access. We further introduce a topic entity anchoring mechanism that grounds questions in the correct graph neighborhood without any runtime inter-silo communication. We evaluate 12 model configurations across three benchmarks and show that FedV-KGQA performs strongly, remains close to centralized performance, generalizes to 3-hop reasoning, and is robust to embedding perturbations.

Md Saikat Islam Khan Bappy, Oshani Seneviratne

Rensselaer Polytechnic Institute, Troy, NY 12180, USA

Knowledge Graph Question AnsweringMulti-Hop QAFederated Learning
AskPDF