RVFL-X: A Novel Randomized Network Based on Complex Transformed Real-Valued Tabular Datasets

2025-10-06

AI Summary

To address the challenge of effectively leveraging complex-valued representations for real-valued tabular data, this paper proposes RVFL-X—the first complex-valued extension of the Random Vector Functional Link network (RVFL). Its core innovations include two complexification strategies: a natural phase-magnitude mapping and an end-to-end complex embedding learning framework driven by an autoencoder; additionally, it introduces a principled complex weight initialization scheme and compatible complex activation functions. RVFL-X preserves RVFL’s architectural simplicity and training efficiency while substantially enhancing representational capacity. Extensive experiments across 80 UCI benchmark datasets demonstrate that RVFL-X consistently outperforms the original RVFL and multiple state-of-the-art randomized neural networks, exhibiting superior robustness and generalization performance.

Technology Category

• Machine Learning: Representation Learning
• Computer Vision: Representation Learning for Vision
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Recent advancements in neural networks, supported by foundational theoretical insights, emphasize the superior representational power of complex numbers. However, their adoption in randomized neural networks (RNNs) has been limited due to the lack of effective methods for transforming real-valued tabular datasets into complex-valued representations. To address this limitation, we propose two methods for generating complex-valued representations from real-valued datasets: a natural transformation and an autoencoder-driven method. Building on these mechanisms, we propose RVFL-X, a complex-valued extension of the random vector functional link (RVFL) network. RVFL-X integrates complex transformations into real-valued datasets while maintaining the simplicity and efficiency of the original RVFL architecture. By leveraging complex components such as input, weights, and activation functions, RVFL-X processes complex representations and produces real-valued outputs. Comprehensive evaluations on 80 real-valued UCI datasets demonstrate that RVFL-X consistently outperforms both the original RVFL and state-of-the-art (SOTA) RNN variants, showcasing its robustness and effectiveness across diverse application domains.

Problem

• Transforming real-valued tabular data into complex representations for neural networks
• Extending RVFL networks with complex-valued components while preserving efficiency
• Improving performance over existing randomized neural networks on diverse datasets

Innovation

• Complex transformation methods for real-valued datasets
• RVFL-X extends RVFL with complex-valued components
• Maintains RVFL efficiency while enhancing performance