The paper proposes graph neural network encoders that transform organized signal sets—such as ordered radar or sensor signals with varying sampling parameters—into fixed‑size vector representations. These embeddings aim to eliminate sampling differences, enabling topology‑aware processing without traditional signal‑processing constraints. The authors evaluate the discriminative power of the embeddings, focusing on waveform separation, using synthetic complex‑valued radiofrequency signals.
arXiv:2608. 01318v1 Announce Type: cross Abstract: Modern sensing, communication, and learning systems generate heterogeneous network signals, with local data differing in dimension, modality, and geometric structure.
Modern sensing, communication, and learning systems generate heterogeneous network signals, with local data differing in dimension, modality, and geometric structure. Processing such data requires a mathematical framework capable of simultaneously modeling heterogeneous local signal spaces and the transformations relating them.
arXiv:2610.19899v1 Announce Type: new Abstract: Neural networks operate naturally on finite-dimensional vectors, yet many problems require reasoning about higher-order objects such as distributions,...
arXiv:2506. 11139v3 Announce Type: replace-cross Abstract: Implicit Neural Representations (INRs) have recently shown impressive results, but their fundamental capacity, implicit biases, and scaling behavior remain poorly understood.
The paper introduces a spatial-frequency-aware implicit neural representation that fuses a Multi‑Layer Perceptron (MLP) branch with a Kolmogorov‑Arnold network (KAN) branch. The MLP captures low‑frequency, smooth structures while the KAN captures high‑frequency, localized details, and their outputs are combined using discrete wavelet transform (DWT) and inverse DWT. A wavelet‑domain band‑separation regularization encourages complementary frequency behavior, and experiments on 1D–4D signals show improved reconstruction fidelity.
arXiv:2607. 20857v1 Announce Type: cross Abstract: Scientific machine learning methods such as neural operators and physics-informed neural networks have advanced engineering applications and inverse problems, but their training typically requires large volumes of simulated data.
The article reviews the problem of learning graph structures from data, noting that research has traditionally split into two paths: inferring the topology of a single graph from observations on it, and learning a generative distribution from multiple observed graphs to sample new ones. It proposes a unified framework that treats both as inverse problems of a common graph generation process, reviews key methods, and discusses their interrelations, strengths, and limitations. The review highlights opportunities for cross‑paradigm integration and outlines future research directions.
arXiv:2412. 19419v2 Announce Type: replace-cross Abstract: Graph neural networks are deep neural networks designed for graphs with attributes attached to nodes or edges.
arXiv:2607. 02166v1 Announce Type: cross Abstract: The rapid advancements in using neural networks as implicit data representations have attracted significant interest in developing machine learning methods that analyze and process the weight spaces of other neural networks.
arXiv:2610.19401v1 Announce Type: new Abstract: As large, powerful pre-trained models become more prevalent, there is growing interest in developing methods that allow different neural networks to be...
arXiv:2607. 10822v1 Announce Type: new Abstract: Indoor spatial understanding remains a fundamental challenge for intelligent systems operating in physical environments.
arXiv:2608. 01160v1 Announce Type: new Abstract: Topological neural networks (TNNs) enable leveraging high-order structures on graphs (e.