Knowledge graphs are increasingly distributed across autonomous organizations that share an entity space but own disjoint subsets of relations, forming a vertical partition. Answering a multi-hop query may require combining facts from several silos, making the partitioning strategy a key data management decision that affects communication, indexing, load balance, and query latency. However, the costs associated with different partitioning strategies remain insufficiently studied. We formalize vertical partitioning as a design space and compare four strategies: semantic domain grouping, frequency-balanced partitioning, co-occurrence graph-cut partitioning, and random partitioning. We evaluate them using five metrics: communication cost, candidate index size, cross-silo path length, load balance, and end-to-end query latency. Three of the five prove to be determined by the graph and the silo count rather than by the partition, which reduces the design problem to two conflicting axes, cross-silo path length and load balance. Experiments on MetaQA and PathQuestion use a fixed federated knowledge graph question-answering architecture based on TransE embeddings and a frozen BERT encoder across three silo configurations. By keeping the learning model unchanged, we isolate the effect of partitioning and show that the trade-off between locality and balance holds only where each silo can hold several relations, weakening as the number of silos increases. The study provides practical guidance for deployments constrained by cross-silo reasoning or by silo load.
Figures & tables
Figure 1: Multi-hop question answering in the vertical federated setting. Silos own disjoint relation subsets over a shared entity space E , so a 2-hop question may chain facts across a silo boundary.
Figure 2: The four partitioning strategies, shown for nine relations across three silos: grouping by topic, equalizing triple counts, keeping chained relations together, and random assignment.
Figure 3: Vertical partitioning as a data-management decision. A strategy Π assigns each relation to one of K silos. The resulting layout is trained on a fixed substrate and characterized along five cost metrics (M1–M5) for K∈{3,5,7} , so that, within each K , differences reflect the partition.
ID
Name
Reported as
Definition
Depends on Π ?
M1
Communication cost
GB per round
Eq. 3
No
M2
Candidate set and index size
Entries per topic entity
Eq. 4
No
M3
Cross-silo path length
Crossing rate per query
Eq. 5
Yes
M4
Load balance
Imbalance, CV of silo sizes
Eq. 6
Yes
M5
Query latency
Mean ms per question
—
No
Table 1: The five cost metrics, the units in which each is reported, and whether it varies with the partition. M3 and M4 are the two axes a partition trades off. The other three are fixed by the graph, the substrate, and the silo count.
Figure 4: The fixed federated question-answering substrate used in all experiments. Each silo trains a local TransE model and uploads entity embeddings. The server fuses them, anchors the question at the topic entity, and scores candidates over a two-hop set. Dashed annotations mark where each cost metric (M1–M5) is incurred.
Dataset
Entities
Relations
Triples
Domain
MetaQA
43,235
15
405,433
movie
PathQuestion
75,043
13
376,847
person-centric
Table 2: Benchmark statistics relevant to partitioning. The relation count is the size of the set being partitioned. The entity count drives communication volume and index size.
MetaQA
PathQuestion
Metric
K
Πdom
Πfreq
Πcut
Πrand
Πdom
Πfreq
Πcut
Πrand
M3: Cross-silo path length (crossing rate)
3
0.019
0.058
0.000
0.048
0.517
0.379
0.276
0.394
5
0.019
0.019
0.000
0.053
0.517
0.448
0.517
0.476
7
0.019
0.019
0.019
0.060
0.517
0.535
0.517
0.503
M4: Load balance (imbalance, CV)
3
0.371
0.018
0.326
0.428
0.609
0.012
0.168
0.321
5
0.946
0.302
0.619
0.656
1.134
0.021
0.661
0.513
Table 3: Partitioning cost results for the two metrics that depend on the partition. M3 is the cross-silo path length of Equation 5 , reported as a crossing rate and measured on held-out test paths. M4 is the load balance metric of Equation 6 , reported as the coefficient of variation of per-silo triple counts. Lower is better for both. Hits@3 on the test split is a quality control, not a result we claim. Πrand is averaged over twenty seeds for M3 and M4 and over three seeds for quality. The best M3 and M4 value in each row is in bold.
Figure 5: Cost metrics versus silo count K . Panels (a,c) show crossing rate (M3) and panels (b,d) load imbalance (M4); lower is better. Crossing rates use held-out test paths, and Πrand is averaged over twenty seeds. Πcut leads on locality at K=3 , while Πfreq consistently minimizes imbalance. Panels (a) and (c) use different vertical scales.
Figure 6: Locality against balance at K=3 , where the trade-off is sharpest. Dashed lines mark the best value achieved on each axis, and no strategy reaches their intersection. Πcut is lowest on crossing rate and Πfreq is leftmost on imbalance, and no strategy is best on both axes. At K≥5 the opposition weakens (Figure 5 ).
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 answering usually assumes that one system can reach the whole graph. In practice, facts are often held by organizations that share entity identifiers but own disjoint relation types, so no single party sees a complete reasoning chain. This poster presents the empirical findings of FedV-KGQA on multi-hop question answering over such vertically partitioned graphs. Each silo enriches its local graph and trains a knowledge graph embedding on its own triples. A server then concatenates the silo-specific entity views, anchors the projected question at the topic entity, and ranks candidates by similarity. Raw triples and relation embeddings never leave a silo. Comparing the FedV-KGQA experiments with one another yields three results. First, federated fusion recovers most of the centralized accuracy, while a single silo recovers little. Second, anchoring and enrichment matter more than the choice of embedding model. Third, the cheapest encoder depends on the target accuracy rather than on parameter count. This poster paper contributes that cross-experiment comparison, four design lessons drawn from it, and an interactive prototype that runs real inference and traces the full pipeline, per question, on released checkpoints.
Md Saikat Islam Khan Bappy, Oshani Seneviratne
Rensselaer Polytechnic Institute, Troy, NY 12180, USA
Retrieval-Augmented Generation (RAG) systems empower large language models (LLMs) with external knowledge, yet struggle with efficiency-accuracy trade-offs when scaling to large knowledge graphs. Existing approaches often rely on monolithic graph retrieval, incurring unnecessary latency for simple queries and fragmented reasoning for complex multi-hop questions. To address these challenges, this paper propose SPLIT-RAG, a multi-agent RAG framework that addresses these limitations with question-driven semantic graph partitioning and collaborative subgraph retrieval. The innovative framework first create Semantic Partitioning of Linked Information, then use the Type-Specialized knowledge base to achieve Multi-Agent RAG. The attribute-aware graph segmentation manages to divide knowledge graphs into semantically coherent subgraphs, ensuring subgraphs align with different query types, while lightweight LLM agents are assigned to partitioned subgraphs, and only relevant partitions are activated during retrieval, thus reduce search space while enhancing efficiency. Finally, a hierarchical merging module resolves inconsistencies across subgraph-derived answers through logical verifications. Extensive experimental validation demonstrates considerable improvements compared to existing approaches.
Ruiyi Yang, Hao Xue, Imran Razzak +3
University of New South Wales Sydney, NSW, Australia · Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi, UAE · Griffith University Queensland, Australia +1