InductWave: Inductive Multi-Hop Logical Query Answering on Knowledge Graphs

Jul 16, 2026

InductWave addresses logical multi-hop query answering on knowledge graphs where implicit completeness assumptions no longer hold under real-world resource constraints. Existing approaches emphasize existential first-order logic (EFO) using conjunction, disjunction, and negation, but are mostly transductive and cannot reason over unseen entities. InductWave introduces a wavelet-based inductive embedding method with fewer message-passing layers, matching baselines while enabling evaluation on massive graphs. Experiments on FB15k-(237) vary train–test graph proportions and show improvements across cases, with code and datasets provided.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

Introduction

Proposed Method

Contributions

Experimental Setup and Results

InductWave: Inductive Multi-Hop Logical Query Answering on Knowledge Graphs Mayank Kharbanda, Michael Cochez, Rajiv Ratn Shah, Raghava Mutharaju arXiv :2607 .07422v 1 [ cs .AI] 8 Jul 2026 Abstract—Logical Multi-Hop Query Answering over Knowledge Graphs (KGs) can be formulated as querying, with an implicit completeness assumption. Current works mainly focus on Existential First Order Logic (EFO) queries. These EFO queries contain conjunction(∧), disjunction (∨), and negation (¬) operators. Most existing works employ transductive reasoning, meaning they are not capable of reasoning over entities unseen during training. In the real world, there is a resource scarcity, and we cannot train a model with all the nodes of a large KG. Hence, we propose InductWave, a wavelet-based inductive embedding method for logical query answering on large KGs. Here, the training graph consists of fewer nodes than the test graph. Our model performs on par with the baseline models while having half the number of message-passing layers. It outperforms all of them in most cases, with 75% of the layers. These fewer resource requirements enable us to evaluate InductWave on massive graphs, such as Wiki-KG. We test our model using extensive experiments across varying train-test graph proportions of the FB15k-(237) dataset, comparing it with the state-of-theart models. The code and datasets for the model are available at [https://github.com/kracr/inductwave/](https://github.com/kracr/inductwave/). Index Terms—Knowledge Graphs, Logical Query Answering, Multi-Hop Query Answering, Inductive Query Answering, Graph Wavelets. I. INTRODUCTION A Knowledge Graph (KG) [1] is a directed graph used to represent facts. It is a set of triples in the form of source, relation, and object. The KGs are used to extract non-trivial information from data by leveraging structural and logical features. These graphs encompass diverse domains, including healthcare, finance, e-commerce, and search. Tasks such as recommendation systems, link prediction, and knowledge retrieval are performed on KGs to extract novel information [2] . Multi-hop logical query answering over KGs involves answering First Order Logic (FOL) queries. It includes traversing more than one hop from a starting node in the KG. Current works mainly focus on Existential First Order Logic (EFO) queries consisting of conjunction (∧), disjunction (∨), and negation (¬) operators. For query answering, there are two primary ways to train a model. First is the transductive method, in which the nodes and relations in the training and test graphs are identical; only the number of triples (edges) in the test graph increases. The other is the inductive method, in which the model is trained on a subset of nodes and/or M. Kharbanda ([mayankk@iiitd.ac.in](mayankk@iiitd.ac.in)) is with IIIT-Delhi, India, and guest at Vrije Universiteit, Amsterdam, The Netherlands. M. Cochez ([michael.cochez@abo.fi](michael.cochez@abo.fi)) is with Ellis Institute Finland and A˚ bo Akademi University, Finland, prior with Vrije Universiteit, Amsterdam, The Netherlands. R. Shah ([rajivratn@iiitd.ac.in](rajivratn@iiitd.ac.in)) is with IIIT-Delhi, India and R. Mutharaju ([raghava@iitpkd.ac.in](raghava@iitpkd.ac.in)) is with IIT Palakkad, Kerala, India. relations and can handle new nodes and/or relations at test time. Current State-Of-The-Art (SOTA). Traditional queryanswering languages, such as SPARQL, become inadequate while processing queries over incomplete or noisy data. To address this, neural logical query answering methods have been introduced. These models embed queries and the KG ina latent space and predict answers against noise and missing links. There has been significant progress in recent years in neural methods for multi-hop logical query answering. At the sametime, most of these methods are transductive. These models require training across all parts of the KG and often fail when encountering new nodes/relations a

FAQs

What problem does InductWave target in logical multi-hop query answering on knowledge graphs?

InductWave targets inductive multi-hop logical query answering under the practical constraint that models cannot be trained on all nodes of a large knowledge graph, unlike mostly transductive prior work.

Which logical query form does the document focus on?

The work focuses on existential first-order logic (EFO) queries that use conjunction (∧), disjunction (∨), and negation (¬) operators.

How does InductWave differ from baseline models in computation and scalability?

InductWave is wavelet-based and achieves baseline-level performance while using fewer message-passing layers, reducing resource requirements and enabling evaluation on massive graphs such as Wiki-KG.

Jul 16, 2026

Upload by Seraphina