Counting Still Counts: Understanding Neural Complex Query Answering Through Query Relaxation

• URL: http://arxiv.org/abs/2511.22565v1
• Date: Thu, 27 Nov 2025 15:57:29 GMT
• Title: Counting Still Counts: Understanding Neural Complex Query Answering Through Query Relaxation
• Authors: Yannick Brunink, Daniel Daza, Yunjie He, Michael Cochez,
• Abstract summary: We compare neural methods for Complex Query Answering (CQA) over knowledge graphs (KGs) with an alternative, training-free query relaxation strategy.<n>We find several cases where neural and relaxation-based approaches perform similarly, with no neural model consistently outperforming the latter.<n>Our findings highlight the importance of stronger non-neural baselines and suggest that future neural approaches could benefit from incorporating principles of query relaxation.
• Score: 6.887078292316648
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Neural methods for Complex Query Answering (CQA) over knowledge graphs (KGs) are widely believed to learn patterns that generalize beyond explicit graph structure, allowing them to infer answers that are unreachable through symbolic query processing. In this work, we critically examine this assumption through a systematic analysis comparing neural CQA models with an alternative, training-free query relaxation strategy that retrieves possible answers by relaxing query constraints and counting resulting paths. Across multiple datasets and query structures, we find several cases where neural and relaxation-based approaches perform similarly, with no neural model consistently outperforming the latter. Moreover, a similarity analysis reveals that their retrieved answers exhibit little overlap, and that combining their outputs consistently improves performance. These results call for a re-evaluation of progress in neural query answering: despite their complexity, current models fail to subsume the reasoning patterns captured by query relaxation. Our findings highlight the importance of stronger non-neural baselines and suggest that future neural approaches could benefit from incorporating principles of query relaxation.

Related papers

• NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering [13.148067007933522]
  NeuroSymActive is a modular framework that combines a differentiable neural-symbolic reasoning layer with an exploration controller for Knowledge Graph Question Answering.<n>We show that NeuroSymActive attains strong answer accuracy while reducing the number of expensive graph lookups and model calls.
  arXiv  Detail & Related papers  (2026-02-17T04:47:29Z)
• KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering [64.62317305868264]
  We present textbfKBQA-R1, a framework that shifts the paradigm from text imitation to interaction optimization via Reinforcement Learning.<n>Treating KBQA as a multi-turn decision process, our model learns to navigate the knowledge base using a list of actions.<n>Experiments on WebQSP, GrailQA, and GraphQuestions demonstrate that KBQA-R1 achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-12-10T17:45:42Z)
• Efficient and Scalable Neural Symbolic Search for Knowledge Graph Complex Query Answering [50.1887329564127]
  We propose an efficient and scalable symbolic search framework for complex queries.<n>Our framework reduces the computational load of symbolic methods by 90% while maintaining nearly the same performance.
  arXiv  Detail & Related papers  (2025-05-13T01:24:09Z)
• Type-based Neural Link Prediction Adapter for Complex Query Answering [2.1098688291287475]
  We propose TypE-based Neural Link Prediction Adapter (TENLPA), a novel model that constructs type-based entity-relation graphs. In order to effectively combine type information with complex logical queries, an adaptive learning mechanism is introduced. Experiments on 3 standard datasets show that TENLPA model achieves state-of-the-art performance on complex query answering.
  arXiv  Detail & Related papers  (2024-01-29T10:54:28Z)
• Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors [58.340159346749964]
  We propose a new neural-symbolic method to support end-to-end learning using complex queries with provable reasoning capability. We develop a new dataset containing ten new types of queries with features that have never been considered. Our method outperforms previous methods significantly in the new dataset and also surpasses previous methods in the existing dataset at the same time.
  arXiv  Detail & Related papers  (2023-04-14T11:35:35Z)
• Adapting Neural Link Predictors for Data-Efficient Complex Query Answering [45.961111441411084]
  We propose a parameter-efficient score emphadaptation model optimised to re-calibrate neural link prediction scores for the complex query answering task. CQD$mathcalA$ produces significantly more accurate results than current state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-01-29T00:17:16Z)
• Logical Message Passing Networks with One-hop Inference on Atomic Formulas [57.47174363091452]
  We propose a framework for complex query answering that decomposes the Knowledge Graph embeddings from neural set operators. On top of the query graph, we propose the Logical Message Passing Neural Network (LMPNN) that connects the local one-hop inferences on atomic formulas to the global logical reasoning. Our approach yields the new state-of-the-art neural CQA model.
  arXiv  Detail & Related papers  (2023-01-21T02:34:06Z)
• Neural Dependencies Emerging from Learning Massive Categories [94.77992221690742]
  This work presents two astonishing findings on neural networks learned for large-scale image classification. 1) Given a well-trained model, the logits predicted for some category can be directly obtained by linearly combining the predictions of a few other categories. 2) Neural dependencies exist not only within a single model, but even between two independently learned models.
  arXiv  Detail & Related papers  (2022-11-21T09:42:15Z)
• Neural-Symbolic Entangled Framework for Complex Query Answering [22.663509971491138]
  We propose a Neural and Entangled framework (ENeSy) for complex query answering. It enables the neural and symbolic reasoning to enhance each other to alleviate the cascading error and KG incompleteness. ENeSy achieves the SOTA performance on several benchmarks, especially in the setting of the training model only with the link prediction task.
  arXiv  Detail & Related papers  (2022-09-19T06:07:10Z)
• Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness [68.97830259849086]
  Most datasets only capture a simpler subproblem and likely suffer from spurious features. We study adversarial robustness - a local generalization property - to reveal hard, model-specific instances and spurious features. Unlike in other applications, where perturbation models are designed around subjective notions of imperceptibility, our perturbation models are efficient and sound. Surprisingly, with such perturbations, a sufficiently expressive neural solver does not suffer from the limitations of the accuracy-robustness trade-off common in supervised learning.
  arXiv  Detail & Related papers  (2021-10-21T07:28:11Z)

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.