# Towards Improved Imbalance Robustness in Continual Multi-Label Learning with Dual Output Spiking Architecture (DOSA)

arXiv: https://arxiv.org/abs/2402.04596 · HTML: https://mlsanity.com/paper/2402.04596/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 45 references that are in the map.
- First posted on arXiv 7 Feb 2024.

## Builds on (most cited first, 18 of 18)

- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks](https://mlsanity.com/paper/2007.05785/) (2020)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [SLAYER: Spike Layer Error Reassignment in Time](https://mlsanity.com/paper/1810.08646/) (2018)
- [Supermasks in Superposition](https://mlsanity.com/paper/2006.14769/) (2020)
- [SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence](https://mlsanity.com/paper/2310.16620/) (2023)
- [Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting](https://mlsanity.com/paper/1802.02950/) (2018)
- [Don't forget, there is more than forgetting: new metrics for Continual Learning](https://mlsanity.com/paper/1810.13166/) (2018)
- [The Emerging Trends of Multi-Label Learning](https://mlsanity.com/paper/2011.11197/) (2020)
- [Fast and energy-efficient neuromorphic deep learning with first-spike times](https://mlsanity.com/paper/1912.11443/) (2019)
- [Bayesian Continual Learning via Spiking Neural Networks](https://mlsanity.com/paper/2208.13723/) (2022)
- [Multi-Label Continual Learning using Augmented Graph Convolutional Network](https://mlsanity.com/paper/2211.14763/) (2022)
- [Continuous learning of spiking networks trained with local rules](https://mlsanity.com/paper/2111.09553/) (2021)
- [Meta-Learning Adaptive Loss Functions](https://mlsanity.com/paper/2301.13247/) (2023)
- [Minimal spiking neuron for solving multi-label classification tasks](https://mlsanity.com/paper/2003.02902/) (2020)

## Abstract (arXiv)

Algorithms designed for addressing typical supervised classification problems can only learn from a fixed set of samples and labels, making them unsuitable for the real world, where data arrives as a stream of samples often associated with multiple labels over time. This motivates the study of task-agnostic continual multi-label learning problems. While algorithms using deep learning approaches for continual multi-label learning have been proposed in the recent literature, they tend to be computationally heavy. Although spiking neural networks (SNNs) offer a computationally efficient alternative to artificial neural networks, existing literature has not used SNNs for continual multi-label learning. Also, accurately determining multiple labels with SNNs is still an open research problem. This work proposes a dual output spiking architecture (DOSA) to bridge these research gaps. A novel imbalance-aware loss function is also proposed, improving the multi-label classification performance of the model by making it more robust to data imbalance. A modified F1 score is presented to evaluate the effectiveness of the proposed loss function in handling imbalance. Experiments on several benchmark multi-label datasets show that DOSA trained with the proposed loss function shows improved robustness to data imbalance and obtains better continual multi-label learning performance than CIFDM, a previous state-of-the-art algorithm.