Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations

• URL: http://arxiv.org/abs/2306.17105v1
• Date: Thu, 29 Jun 2023 17:07:34 GMT
• Title: Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations
• Abstract summary: Recent work has observed an intriguing ''Neural Collapse'' phenomenon in well-trained neural networks. This appears to suggest that the last-layer representations are completely determined by the labels. We show that the apparent collapse hides important fine-grained structure in the representations.
• Score: 28.249932563821712
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent work has observed an intriguing ''Neural Collapse'' phenomenon in well-trained neural networks, where the last-layer representations of training samples with the same label collapse into each other. This appears to suggest that the last-layer representations are completely determined by the labels, and do not depend on the intrinsic structure of input distribution. We provide evidence that this is not a complete description, and that the apparent collapse hides important fine-grained structure in the representations. Specifically, even when representations apparently collapse, the small amount of remaining variation can still faithfully and accurately captures the intrinsic structure of input distribution. As an example, if we train on CIFAR-10 using only 5 coarse-grained labels (by combining two classes into one super-class) until convergence, we can reconstruct the original 10-class labels from the learned representations via unsupervised clustering. The reconstructed labels achieve $93\%$ accuracy on the CIFAR-10 test set, nearly matching the normal CIFAR-10 accuracy for the same architecture. We also provide an initial theoretical result showing the fine-grained representation structure in a simplified synthetic setting. Our results show concretely how the structure of input data can play a significant role in determining the fine-grained structure of neural representations, going beyond what Neural Collapse predicts.

Related papers

• Complexity Induction: Compositional Generalization via Structured Training Distortion [51.56484100374058]
  We show that structured distortion of training data can induce compositional generalization without architectural modification.<n>Results suggest that structured complication of training signals can influence both the internal organization of learned representations and their compositional interpretation.
  arXiv  Detail & Related papers  (2026-08-21T00:45:02Z)
• The role of class encoding in neural collapse [0.0]
  We explore the role of label encoding in neural collapse by relying on the unrestricted feature model with mean squared error training loss.<n>We show that for one-hot encoded labels and balanced data, the uncentered mean features associated with each class coefficient transition from a simplexangular tight frame to an equixangular tight frame.<n>For any arbitrary encoding, we also show that the final classifier's bias aims at centering the labels, compensating for the discrepancy between the global mean of the labels and the origin.
  arXiv  Detail & Related papers  (2026-05-29T20:34:07Z)
• Semantic Loss Functions for Neuro-Symbolic Structured Prediction [74.18322585177832]
  We discuss the semantic loss, which injects knowledge about such structure, defined symbolically, into training. It is agnostic to the arrangement of the symbols, and depends only on the semantics expressed thereby. It can be combined with both discriminative and generative neural models.
  arXiv  Detail & Related papers  (2024-05-12T22:18:25Z)
• Inducing Neural Collapse in Deep Long-tailed Learning [13.242721780822848]
  We propose two explicit feature regularization terms to learn high-quality representation for class-imbalanced data. With the proposed regularization, Neural Collapse phenomena will appear under the class-imbalanced distribution. Our method is easily implemented, highly effective, and can be plugged into most existing methods.
  arXiv  Detail & Related papers  (2023-02-24T05:07:05Z)
• Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning [120.53458753007851]
  Few-shot class-incremental learning (FSCIL) has been a challenging problem as only a few training samples are accessible for each novel class in the new sessions. We deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse. We propose a neural collapse inspired framework for FSCIL. Experiments on the miniImageNet, CUB-200, and CIFAR-100 datasets demonstrate that our proposed framework outperforms the state-of-the-art performances.
  arXiv  Detail & Related papers  (2023-02-06T18:39:40Z)
• Understanding Imbalanced Semantic Segmentation Through Neural Collapse [81.89121711426951]
  We show that semantic segmentation naturally brings contextual correlation and imbalanced distribution among classes. We introduce a regularizer on feature centers to encourage the network to learn features closer to the appealing structure. Our method ranks 1st and sets a new record on the ScanNet200 test leaderboard.
  arXiv  Detail & Related papers  (2023-01-03T13:51:51Z)
• Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data [12.225207401994737]
  We show that complex systems with massive amounts of parameters exhibit the same structural properties when training until convergence. In particular, it has been observed that the last-layer features collapse to their class-means. Our results demonstrate the convergence of the last-layer features and classifiers to a geometry consisting of vectors.
  arXiv  Detail & Related papers  (2023-01-01T16:29:56Z)
• Isometric Representations in Neural Networks Improve Robustness [0.0]
  We train neural networks to perform classification while simultaneously maintaining within-class metric structure. We verify that isometric regularization improves the robustness to adversarial attacks on MNIST.
  arXiv  Detail & Related papers  (2022-11-02T16:18:18Z)
• Do We Really Need a Learnable Classifier at the End of Deep Neural Network? [118.18554882199676]
  We study the potential of learning a neural network for classification with the classifier randomly as an ETF and fixed during training. Our experimental results show that our method is able to achieve similar performances on image classification for balanced datasets.
  arXiv  Detail & Related papers  (2022-03-17T04:34:28Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• Mitigating Generation Shifts for Generalized Zero-Shot Learning [52.98182124310114]
  Generalized Zero-Shot Learning (GZSL) is the task of leveraging semantic information (e.g., attributes) to recognize the seen and unseen samples, where unseen classes are not observable during training. We propose a novel Generation Shifts Mitigating Flow framework for learning unseen data synthesis efficiently and effectively. Experimental results demonstrate that GSMFlow achieves state-of-the-art recognition performance in both conventional and generalized zero-shot settings.
  arXiv  Detail & Related papers  (2021-07-07T11:43:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.