# CoSupFormer : A Contrastive Supervised learning approach for EEG signal Classification

arXiv: https://arxiv.org/abs/2509.20489 · HTML: https://mlsanity.com/paper/2509.20489/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 56 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://mlsanity.com/paper/2310.06625/) (2023)
- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [Time-Series Representation Learning via Temporal and Contextual Contrasting](https://mlsanity.com/paper/2106.14112/) (2021)
- [Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI](https://mlsanity.com/paper/2405.18765/) (2024)
- [CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding](https://mlsanity.com/paper/2412.07236/) (2024)
- [Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting](https://mlsanity.com/paper/2402.05956/) (2024)
- [NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals](https://mlsanity.com/paper/2409.00101/) (2024)
- [EEG-TCNet: An Accurate Temporal Convolutional Network for Embedded Motor-Imagery Brain-Machine Interfaces](https://mlsanity.com/paper/2006.00622/) (2020)
- [Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting](https://mlsanity.com/paper/2206.04038/) (2022)
- [Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification](https://mlsanity.com/paper/2405.19363/) (2024)
- [Multi-resolution Time-Series Transformer for Long-term Forecasting](https://mlsanity.com/paper/2311.04147/) (2023)
- [Data augmentation for learning predictive models on EEG: a systematic comparison](https://mlsanity.com/paper/2206.14483/) (2022)
- [You Can't Ignore Either: Unifying Structure and Feature Denoising for Robust Graph Learning](https://mlsanity.com/paper/2408.00700/) (2024)
- [BioMamba: Leveraging Spectro-Temporal Embedding in Bidirectional Mamba for Enhanced Biosignal Classification](https://mlsanity.com/paper/2503.11741/) (2025)
- [Loss of brain inter-frequency hubs in Alzheimer's disease](https://mlsanity.com/paper/1701.00096/) (2016)

## Built on by (most cited first, 1 of 1)

- [SpecMoE: Spectral Mixture-of-Experts Foundation Model for Cross-Species EEG Decoding](https://mlsanity.com/paper/2603.16739/) (2026)

## Abstract (arXiv)

Electroencephalography signals (EEGs) contain rich multi-scale information crucial for understanding brain states, with potential applications in diagnosing and advancing the drug development landscape. However, extracting meaningful features from raw EEG signals while handling noise and channel variability remains a major challenge. This work proposes a novel end-to-end deep-learning framework that addresses these issues through several key innovations. First, we designed an encoder capable of explicitly capturing multi-scale frequency oscillations covering a wide range of features for different EEG-related tasks. Secondly, to model complex dependencies and handle the high temporal resolution of EEGs, we introduced an attention-based encoder that simultaneously learns interactions across EEG channels and within localized em patches of individual channels. We integrated a dedicated gating network on top of the attention encoder to dynamically filter out noisy and non-informative channels, enhancing the reliability of EEG data. The entire encoding process is guided by a novel loss function, which leverages supervised and contrastive learning, significantly improving model generalization. We validated our approach in multiple applications, ranging from the classification of effects across multiple Central Nervous System (CNS) disorders treatments to the diagnosis of Parkinson's and Alzheimer's disease. Our results demonstrate that the proposed learning paradigm can extract biologically meaningful patterns from raw EEG signals across different species, autonomously select high-quality channels, and achieve robust generalization through innovative architectural and loss design.