EEG-FSL: An EEG-Based Few-Shot Learning Framework for Music Recommendation

Brain-computer interface based on electroencephalogram (EEG) has demonstrated significant potential for capturing users' implicit preferences, offering an innovative technique for music recommendation. However, we face two key challenges: (1) ineffective distinction of complex neural patterns in EEG signals, and (2) the cold-start problem, due to limited user EEG samples. To address these issues, we present EEG-FSL, a novel framework that integrates model-agnostic meta-learning (MAML) with dual-path neural feature extraction for music recommendation. EEG-FSL applies an attention-enhanced EEG encoder to extract meaningful patterns from brain signals through complementary pathways: one pathway retains temporal and phase information, while the other focuses on extracting common frequency-domain features. Furthermore, we utilize contrastive learning to explore the intrinsic structure of the data, significantly improving the model's feature differentiation ability. Additionally, we propose a meta-learning method which allows EEG-FSL to quickly adapt to new users using only a small number of EEG samples, effectively solving cold-start problem. Extensive experiments are conducted on a real-world dataset demonstrate the effectiveness of the proposed method. Specially, in few-shot scenarios, compared to the best baseline, our approach improves mean squared error in score prediction by 8.4% and classification accuracy by 16.8%. Consequently, our work provides a practical solution for next-generation brain-computer interface applications, capable of delivering highly personalized content recommendations while minimizing user data collection requirements. Our code is available at https://anonymous.4open.science/r/EEG-FSL-code-72F3/.

• Publication year

  2025

• Venue

  International Conference on Information and Knowledge Management

• Publication date

  2025-11-10

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1145/3746252.3761201
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Introducing EEG Analyses to Help Personal Music Preference Prediction

  2024influential reference
• A Survey of Music Recommendation Systems

  2024cited by this paper
• Self-Supervised EEG Representation Learning for Robust Emotion Recognition

  2024influential reference
• EEG-SVRec: An EEG Dataset with User Multidimensional Affective Engagement Labels in Short Video Recommendation

  2024cited by this paper
• Multi-View Enhanced Graph Attention Network for Session-Based Music Recommendation

  2023cited by this paper
• AutoEER: automatic EEG-based emotion recognition with neural architecture search

  2023cited by this paper
• Meta-Learning with Adaptive Weighted Loss for Imbalanced Cold-Start Recommendation

  2023cited by this paper
• A Brainwave-based Attention Diagnosis and Music Recommendation System for Reading Improvement

  2021cited by this paper
• Learning to Learn a Cold-start Sequential Recommender

  2021cited by this paper
• Content-driven Music Recommendation: Evolution, State of the Art, and Challenges

  2021cited by this paper
• MAMO: Memory-Augmented Meta-Optimization for Cold-start Recommendation

  2020cited by this paper
• Exploring Acoustic Similarity for Novel Music Recommendation

  2020cited by this paper
• Cold-start Sequential Recommendation via Meta Learner

  2020cited by this paper
• An Efficient LSTM Network for Emotion Recognition From Multichannel EEG Signals

  2020cited by this paper
• Improving Implicit Recommender Systems with Auxiliary Data

  2020cited by this paper
• MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation

  2019cited by this paper
• xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems

  2018cited by this paper
• Self-Attentive Sequential Recommendation

  2018cited by this paper
• Emotion Recognition based on EEG using LSTM Recurrent Neural Network

  2017cited by this paper
• Understanding Error Propagation in Deep Learning Neural Network (DNN) Accelerators and Applications

  2017cited by this paper
• A Simple Neural Attentive Meta-Learner

  2017cited by this paper
• LightGBM: A Highly Efficient Gradient Boosting Decision Tree

  2017cited by this paper
• Music Recommendation

  2016cited by this paper
• Sound and Music Recommendation with Knowledge Graphs

  2016cited by this paper
• A collaborative filtering method for music recommendation using playing coefficients for artists and users

  2016cited by this paper
• Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks

  2015cited by this paper
• Siamese Neural Networks for One-Shot Image Recognition

  2015cited by this paper
• Exploring user emotion in microblogs for music recommendation

  2015cited by this paper
• Improving Content-based and Hybrid Music Recommendation using Deep Learning

  2014cited by this paper
• Music Recommendation and Discovery - The Long Tail, Long Fail, and Long Play in the Digital Music Space

  2010cited by this paper
• Convolutional Neural Network with embedded Fourier Transform for EEG classification

  2008cited by this paper
• Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions

  2005cited by this paper
• Random Forests

  2001cited by this paper
• Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences

  1998cited by this paper
• Time-frequency distributions-a review

  1989cited by this paper

• No citing papers are available for this paper.