arXiv subjects

Angelos-Nikolaos Kanatas

Publications and source records attributed to Angelos-Nikolaos Kanatas.

4 recordsLinked to original sources

arXiv2026

What Makes a Good Layer? Assessing the Layer-Wise Intrinsic Properties of Music Foundation Models

Music foundation models are commonly used as frozen audio feature extractors, yet selecting which layer to extract from remains largely heuristic. Current practice defaults to fixed depths or multi-layer fusion, with limited understanding of why certain layers transfer better across downstream tasks or how representation quality varies with depth and pre-training paradigm. We conduct a systematic layer-wise analysis of 12 music foundation models spanning three pre-training paradigms (masked modeling, autoregressive modeling, and contrastive learning), characterizing their hidden representations through intrinsic geometric and transformation-based properties. Correlating label-free representation-quality metrics with layer-wise performance across 15 downstream tasks, we find that several metrics track layer quality for genre classification, emotion recognition, automatic tagging, and beat tracking, albeit with varying strength across tasks and pre-training paradigms. However, all metrics fail on tonal tasks such as key estimation and chord recognition, indicating that no single property serves as a general proxy for representation quality across music information retrieval tasks. To address this gap, we introduce a pitch-transposition equivariance measure that captures properties missed by these standard metrics, providing a consistent indicator of tonal quality across model families. Finally, we show that intrinsic metrics can serve as effective proxies for layer selection, matching or outperforming trainable multi-layer fusion methods, particularly in limited-data settings.

cs.SD↗

arXiv2025

Evasive Active Hypothesis Testing with Deep Neuroevolution: The Single- and Multi-Agent Cases

Active hypothesis testing is a thoroughly studied problem that finds numerous applications in wireless communications and sensor networks. In this paper, we focus on one centralized and one decentralized problem of active hypothesis testing in the presence of an eavesdropper. For the centralized problem including a single legitimate agent, we present a new framework based on deep NeuroEvolution (NE), whereas, for the decentralized problem, we develop a novel NE-based method for solving collaborative multi-agent tasks, which, interestingly, maintains all computational benefits of our single-agent NE-based scheme. To further reduce the computational complexity of the latter scheme, a novel multi-agent joint NE and pruning framework is also designed. The superiority of the proposed NE-based evasive active hypothesis testing schemes over conventional active hypothesis testing policies, as well as learning-based methods, is validated through extensive numerical investigations in an example use case of anomaly detection over wireless sensor networks. It is demonstrated that the proposed joint optimization and pruning framework achieves nearly identical performance with its unpruned counterpart, while removing a very large percentage of redundant deep neural network weights.

cs.AI↗

arXiv2025

CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning

Recent advances in music foundation models have improved audio representation learning, yet their effectiveness across diverse musical traditions remains limited. We introduce CultureMERT-95M, a multi-culturally adapted foundation model developed to enhance cross-cultural music representation learning and understanding. To achieve this, we propose a two-stage continual pre-training strategy that integrates learning rate re-warming and re-decaying, enabling stable adaptation even with limited computational resources. Training on a 650-hour multi-cultural data mix, comprising Greek, Turkish, and Indian music traditions, results in an average improvement of 4.9% in ROC-AUC and AP across diverse non-Western music auto-tagging tasks, surpassing prior state-of-the-art, with minimal forgetting on Western-centric benchmarks. We further investigate task arithmetic, an alternative approach to multi-cultural adaptation that merges single-culture adapted models in the weight space. Task arithmetic performs on par with our multi-culturally trained model on non-Western auto-tagging tasks and shows no regression on Western datasets. Cross-cultural evaluation reveals that single-culture models transfer with varying effectiveness across musical traditions, whereas the multi-culturally adapted model achieves the best overall performance. To support research on world music representation learning, we publicly release CultureMERT-95M and CultureMERT-TA-95M, fostering the development of more culturally aware music foundation models.

cs.SD↗

arXiv2025

Multi-Agent Actor-Critic with Harmonic Annealing Pruning for Dynamic Spectrum Access Systems

Multi-Agent Deep Reinforcement Learning (MADRL) has emerged as a powerful tool for optimizing decentralized decision-making systems in complex settings, such as Dynamic Spectrum Access (DSA). However, deploying deep learning models on resource-constrained edge devices remains challenging due to their high computational cost. To address this challenge, in this paper, we present a novel sparse recurrent MARL framework integrating gradual neural network pruning into the independent actor global critic paradigm. Additionally, we introduce a harmonic annealing sparsity scheduler, which achieves comparable, and in certain cases superior, performance to standard linear and polynomial pruning schedulers at large sparsities. Our experimental investigation demonstrates that the proposed DSA framework can discover superior policies, under diverse training conditions, outperforming conventional DSA, MADRL baselines, and state-of-the-art pruning techniques.

cs.LG↗