This study compares Transformer-based models and Graph Neural Networks (GNNs) for fake news detection across three datasets: FakeNewsNet, ISOT, and WELFake. Transformer models (BERT, RoBERTa, GPT-2) demonstrated superior performance, achieving mean accuracies above 85% on FakeNewsNet and exceeding 98% on ISOT and WELFake. Specifically, RoBERTa achieved 86.16% accuracy on FakeNewsNet and 99.99% on ISOT, while GPT-2 reached 99.72% on WELFake. In contrast, GNNs (GCN, GraphSAGE, GIN, GAT) exhibited lower performance. GCN achieved 71% accuracy on FakeNewsNet but dropped to 53.30% on ISOT and 50.28% on WELFake, with F1 scores reflecting similar trends. Other GNNs, like GraphSAGE, showed even lower results, particularly on ISOT and WELFake, where performance hovered around 50%. Our findings indicate that while Transformers provide exceptional accuracy and reliability, GNNs offer potential efficiency benefits for resource-constrained scenarios despite their lower predictive performance. This study informs model selection for fake news detection tasks and encourages the exploration of hybrid approaches to balance accuracy and computational efficiency.

This paper presents the application of Kolmogorov-Arnold Networks (KAN) in classifying metal surface defects. Specifically, steel surfaces are analyzed to detect defects such as cracks, inclusions, patches, pitted surfaces, and scratches. Drawing on the Kolmogorov-Arnold theorem, KAN provides a novel approach compared to conventional multilayer perceptrons (MLPs), facilitating more efficient function approximation by utilizing spline functions. The results show that KAN networks can achieve better accuracy than convolutional neural networks (CNNs) with fewer parameters, resulting in faster convergence and improved performance in image classification.

Neural Architecture Search (NAS) aims to automate the design of neural network architectures, reducing the need for manual expert-driven engineering. Evolutionary approaches, such as Cartesian Genetic Programming (CGP), provide a flexible graph-based representation for evolving neural structures but suffer from high computational costs due to expensive fitness evaluations. In this paper, we propose a Surrogate-Assisted Dynamic Cartesian Genetic Programming (SA-DCGP) framework for automated neural architecture design in graph clustering tasks. The framework evolves architectures composed of FastKAN-based nonlinear blocks and SGCC-style linear normalized layers using dynamic mutation and multiple crossover operators. To reduce evaluation cost, we introduce a pair-wise surrogate model that predicts whether an offspring architecture will outperform its parent based on genotype-derived features and cheap training signals. The surrogate guides selection, enabling full training only for promising candidates. We employ a two-stage evaluation protocol with a cheap training phase for surrogate feature extraction and a full training phase for selected architectures. Clustering performance is evaluated using Accuracy, NMI, ARI, and F1 scores. Experimental results on benchmark graph datasets show that SA-DCGP discovers compact and high-performing architectures while significantly reducing computational overhead, demonstrating the effectiveness of surrogate-assisted evolutionary search for graph-based representation learning.