2000 character limit reached
Exploring the Evolution of Hidden Activations with Live-Update Visualization (2405.15135v1)
Published 24 May 2024 in cs.LG
Abstract: Monitoring the training of neural networks is essential for identifying potential data anomalies, enabling timely interventions and conserving significant computational resources. Apart from the commonly used metrics such as losses and validation accuracies, the hidden representation could give more insight into the model progression. To this end, we introduce SentryCam, an automated, real-time visualization tool that reveals the progression of hidden representations during training. Our results show that this visualization offers a more comprehensive view of the learning dynamics compared to basic metrics such as loss and accuracy over various datasets. Furthermore, we show that SentryCam could facilitate detailed analysis such as task transfer and catastrophic forgetting to a continual learning setting. The code is available at https://github.com/xianglinyang/SentryCam.
- Deep learning through the lens of example difficulty. In A. Beygelzimer, Y. Dauphin, P. Liang, and J. Wortman Vaughan, editors, Advances in Neural Information Processing Systems, 2021. URL https://openreview.net/forum?id=WWRBHhH158K.
- Food-101–mining discriminative components with random forests. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VI 13, pages 446–461. Springer, 2014.
- Diffusion maps. Applied and computational harmonic analysis, 21(1):5–30, 2006.
- Visualizing the phate of neural networks. Advances in neural information processing systems, 32, 2019.
- Reducing the dimensionality of data with neural networks. science, 313(5786):504–507, 2006.
- Batch normalization: accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37, ICML’15, page 448–456. JMLR.org, 2015.
- Concept-monitor: Understanding dnn training through individual neurons, 2023.
- Learning multiple layers of features from tiny images. 2009.
- Characterizing datapoints via second-split forgetting, 2022.
- Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426, 2018.
- Phate: a dimensionality reduction method for visualizing trajectory structures in high-dimensional biological data. BioRxiv, 120378, 2017.
- Topological autoencoders. In International conference on machine learning, pages 7045–7054. PMLR, 2020.
- Continual deep learning by functional regularisation of memorable past. In H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin, editors, Advances in Neural Information Processing Systems, volume 33, pages 4453–4464. Curran Associates, Inc., 2020. URL https://proceedings.neurips.cc/paper_files/paper/2020/file/2f3bbb9730639e9ea48f309d9a79ff01-Paper.pdf.
- Conceptevo: Interpreting concept evolution in deep learning training. arXiv preprint arXiv:2203.16475, 2022.
- Continual normalization: Rethinking batch normalization for online continual learning. In International Conference on Learning Representations, 2022. URL https://openreview.net/forum?id=vwLLQ-HwqhZ.
- Identifying mislabeled data using the area under the margin ranking, 2020.
- Experience replay for continual learning. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 32. Curran Associates, Inc., 2019. URL https://proceedings.neurips.cc/paper_files/paper/2019/file/fa7cdfad1a5aaf8370ebeda47a1ff1c3-Paper.pdf.
- Parametric umap embeddings for representation and semi-supervised learning, 2021.
- Dataset cartography: Mapping and diagnosing datasets with training dynamics. In Proceedings of EMNLP, 2020. URL https://arxiv.org/abs/2009.10795.
- An empirical study of example forgetting during deep neural network learning. arXiv preprint arXiv:1812.05159, 2018.
- Three types of incremental learning. Nature Machine Intelligence, 4:1185–1197, 2022.
- Laurens Van der Maaten and Geoffrey Hinton. Visualizing data using t-sne. Journal of machine learning research, 9(11), 2008.
- Temporality spatialization: A scalable and faithful time-travelling visualization for deep classifier training. In IJCAI, pages 4022–4028, 2022a.
- Deepvisualinsight: Time-travelling visualization for spatio-temporal causality of deep classification training. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 5359–5366, 2022b.