From Eigenmodes to Proofs: Integrating Graph Spectral Operators with Symbolic Interpretable Reasoning

• URL: http://arxiv.org/abs/2509.07017v1
• Date: Sun, 07 Sep 2025 01:12:20 GMT
• Title: From Eigenmodes to Proofs: Integrating Graph Spectral Operators with Symbolic Interpretable Reasoning
• Authors: Andrew Kiruluta, Priscilla Burity,
• Abstract summary: We introduce Spectral NSR, a fully spectral neuro-symbolic reasoning framework.<n>It embeds logical rules as spectral templates and performs inference directly in the graph spectral domain.<n>We show that Spectral NSR achieves superior accuracy, faster inference, improved robustness to adversarial perturbations, and higher interpretability compared to leading baselines.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce Spectral NSR, a fully spectral neuro-symbolic reasoning framework that embeds logical rules as spectral templates and performs inference directly in the graph spectral domain. By leveraging graph signal processing (GSP) and frequency-selective filters grounded in the Laplacian eigenstructure of knowledge graphs, the architecture unifies the interpretability of symbolic reasoning with the scalability and adaptability of spectral learning. Beyond the core formulation, we incorporate a comprehensive set of extensions, including dynamic graph and basis learning, rational and diffusion filters for sharper spectral selectivity, mixture-of-spectral-experts for modular specialization, proof-guided training with spectral curricula, and uncertainty quantification for calibrated confidence. Additional enhancements such as large language model coupling, co-spectral transfer alignment, adversarial robustness, efficient GPU kernels, generalized Laplacians, and causal interventions further expand the versatility of the framework. Empirical evaluation on state-of-the-art reasoning benchmarks such as ProofWriter and CLUTRR demonstrates that Spectral NSR achieves superior accuracy, faster inference, improved robustness to adversarial perturbations, and higher interpretability compared to leading baselines including transformers, message-passing neural networks, and neuro-symbolic logic programming systems. Spectral attribution and proof-band agreement analyses confirm that model decisions align closely with symbolic proof structures, while transfer experiments validate effective domain adaptation through co-spectral alignment. These results establish Spectral NSR as a scalable and principled foundation for the next generation of reasoning systems, offering transparency, robustness, and generalization beyond conventional approaches.

Related papers

• RKHS Representation of Algebraic Convolutional Filters with Integral Operators [111.57971404925486]
  In this paper, we develop a theory showing that the range of integral operators naturally induces RKHS convolutional signal models.<n>We show that filtering with integral operators corresponds to iterated box products, giving rise to a unital kernel algebra.<n>Our results establish precise connections between eigendecompositions and RKHS representations in graphon signal processing, extend naturally to directed graphons, and enable novel spatial-spectral localization results.
  arXiv  Detail & Related papers  (2026-02-22T08:28:34Z)
• Spectral Gating Networks [65.9496901693099]
  We introduce Spectral Gating Networks (SGN) to introduce frequency-rich expressivity in feed-forward networks.<n>SGN augments a standard activation pathway with a compact spectral pathway and learnable gates that allow the model to start from a stable base behavior.<n>It consistently improves accuracy-efficiency trade-offs under comparable computational budgets.
  arXiv  Detail & Related papers  (2026-02-07T20:00:49Z)
• SIGMA: Scalable Spectral Insights for LLM Collapse [51.863164847253366]
  We introduce SIGMA (Spectral Inequalities for Gram Matrix Analysis), a unified framework for model collapse.<n>By utilizing benchmarks that deriving and deterministic bounds on the matrix's spectrum, SIGMA provides a mathematically grounded metric to track the contraction of the representation space.<n>We demonstrate that SIGMA effectively captures the transition towards states, offering both theoretical insights into the mechanics of collapse.
  arXiv  Detail & Related papers  (2026-01-06T19:47:11Z)
• Spectral Neuro-Symbolic Reasoning II: Semantic Node Merging, Entailment Filtering, and Knowledge Graph Alignment [0.0]
  This report extends the Spectral Neuro-Symbolic Reasoning (Spectral NSR) framework by introducing three semantically grounded enhancements.<n>The novelty lies in performing semantic and symbolic refinement entirely upstream of the spectral inference stage.<n>The result is a more robust, interpretable, and scalable reasoning system suitable for deployment in open-domain and real-world settings.
  arXiv  Detail & Related papers  (2025-11-02T21:57:15Z)
• A Fully Spectral Neuro-Symbolic Reasoning Architecture with Graph Signal Processing as the Computational Backbone [0.0]
  We propose a fully spectral, neuro-symbolic reasoning architecture that leverages Graph Signal Processing (GSP) as the primary computational backbone.<n>We present a complete mathematical framework for spectral reasoning, including graph Fourier transforms, band-selective attention, and spectral rule grounding.
  arXiv  Detail & Related papers  (2025-08-19T05:49:28Z)
• Quantum Spectral Reasoning: A Non-Neural Architecture for Interpretable Machine Learning [0.0]
  We propose a novel machine learning architecture that departs from conventional neural network paradigms.<n>We use quantum spectral methods, specifically Pade approximants and the Lanczos algorithm, for interpretable signal analysis and symbolic reasoning.<n>Our results show that this spectral-symbolic architecture achieves competitive accuracy while maintaining interpretability and data efficiency.
  arXiv  Detail & Related papers  (2025-08-05T07:16:45Z)
• Optimized Spectral Fault Receptive Fields for Diagnosis-Informed Prognosis [8.719982934025415]
  Spectral Fault Receptive Fields (SFRFs) is a technique for degradation state assessment in bearing fault diagnosis and remaining useful life estimation.<n>SFRFs are designed as antagonistic spectral filters centered on characteristic fault frequencies.<n>A multi-objective evolutionary optimization strategy is employed to tune the receptive field parameters.
  arXiv  Detail & Related papers  (2025-06-14T07:12:56Z)
• Adaptive Branch Specialization in Spectral-Spatial Graph Neural Networks for Certified Robustness [3.2771631221674333]
  In this paper, we explicitly specialize each branch of a Graph Neural Network (GNN)<n>The spectral network is trained to withstand l0 edge perturbations and capture homophilic structures, while the spatial part is designed to resist linf perturbations and heterophilic patterns.<n>A context-aware gating network adaptively fuses the two representations, dynamically routing each node's node to a more reliable branch.
  arXiv  Detail & Related papers  (2025-05-13T08:00:16Z)
• CARL: Camera-Agnostic Representation Learning for Spectral Image Analysis [75.25966323298003]
  Spectral imaging offers promising applications across diverse domains, including medicine and urban scene understanding.<n> variability in channel dimensionality and captured wavelengths among spectral cameras impede the development of AI-driven methodologies.<n>We introduce $textbfCARL$, a model for $textbfC$amera-$textbfA$gnostic $textbfR$esupervised $textbfL$ across RGB, multispectral, and hyperspectral imaging modalities.
  arXiv  Detail & Related papers  (2025-04-27T13:06:40Z)
• Hallucination Detection in LLMs with Topological Divergence on Attention Graphs [64.74977204942199]
  Hallucination, i.e., generating factually incorrect content, remains a critical challenge for large language models.<n>We introduce TOHA, a TOpology-based HAllucination detector in the RAG setting.
  arXiv  Detail & Related papers  (2025-04-14T10:06:27Z)
• Inductive Gradient Adjustment For Spectral Bias In Implicit Neural Representations [17.832898905413877]
  Implicit Neural Representations (INRs) have achieved success in various computer vision tasks.<n>Due to the spectral bias of the vanilla multi-layer perceptrons (MLPs), existing methods focus on designings with sophisticated architectures.<n>We propose a practical Inductive Gradient Adjustment (IGA) method, which could purposefully improve the spectral bias.
  arXiv  Detail & Related papers  (2024-10-17T06:51:10Z)
• Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical Space [54.13671100638092]
  Holistic Physics Mixer (HPM) is a framework for integrating spectral and physical information in a unified space.<n>We show that HPM consistently outperforms state-of-the-art methods in both accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2024-10-15T08:19:39Z)
• HoloNets: Spectral Convolutions do extend to Directed Graphs [59.851175771106625]
  Conventional wisdom dictates that spectral convolutional networks may only be deployed on undirected graphs. Here we show this traditional reliance on the graph Fourier transform to be superfluous. We provide a frequency-response interpretation of newly developed filters, investigate the influence of the basis used to express filters and discuss the interplay with characteristic operators on which networks are based.
  arXiv  Detail & Related papers  (2023-10-03T17:42:09Z)

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.