On Layer-wise Representation Similarity: Application for Multi-Exit Models with a Single Classifier

• URL: http://arxiv.org/abs/2406.14479v1
• Date: Thu, 20 Jun 2024 16:41:09 GMT
• Title: On Layer-wise Representation Similarity: Application for Multi-Exit Models with a Single Classifier
• Authors: Jiachen Jiang, Jinxin Zhou, Zhihui Zhu,
• Abstract summary: We study the similarity of representations between the hidden layers of individual transformers. We propose an aligned training approach to enhance the similarity between internal representations.
• Score: 20.17288970927518
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Analyzing the similarity of internal representations within and across different models has been an important technique for understanding the behavior of deep neural networks. Most existing methods for analyzing the similarity between representations of high dimensions, such as those based on Canonical Correlation Analysis (CCA) and widely used Centered Kernel Alignment (CKA), rely on statistical properties of the representations for a set of data points. In this paper, we focus on transformer models and study the similarity of representations between the hidden layers of individual transformers. In this context, we show that a simple sample-wise cosine similarity metric is capable of capturing the similarity and aligns with the complicated CKA. Our experimental results on common transformers reveal that representations across layers are positively correlated, albeit the similarity decreases when layers are far apart. We then propose an aligned training approach to enhance the similarity between internal representations, with trained models that enjoy the following properties: (1) the last-layer classifier can be directly applied right after any hidden layers, yielding intermediate layer accuracies much higher than those under standard training, (2) the layer-wise accuracies monotonically increase and reveal the minimal depth needed for the given task, (3) when served as multi-exit models, they achieve on-par performance with standard multi-exit architectures which consist of additional classifiers designed for early exiting in shallow layers. To our knowledge, our work is the first to show that one common classifier is sufficient for multi-exit models. We conduct experiments on both vision and NLP tasks to demonstrate the performance of the proposed aligned training.

Related papers

• Representation Similarity: A Better Guidance of DNN Layer Sharing for Edge Computing without Training [3.792729116385123]
  We propose a new model merging scheme by sharing representations at the edge, guided by representation similarity S. We show that S is extremely highly correlated with merged model's accuracy with Pearson Correlation Coefficient |r| > 0.94 than other metrics.
  arXiv  Detail & Related papers  (2024-10-15T03:35:54Z)
• Weighted Point Cloud Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric [44.95433989446052]
  We show the benefit of our proposed method through a new understanding of the contrastive loss of CLIP. We show that our proposed similarity based on weighted point clouds consistently achieves the optimal similarity.
  arXiv  Detail & Related papers  (2024-04-30T03:15:04Z)
• S^2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in OR [50.435592120607815]
  Scene graph generation (SGG) of surgical procedures is crucial in enhancing holistically cognitive intelligence in the operating room (OR) Previous works have primarily relied on multi-stage learning, where the generated semantic scene graphs depend on intermediate processes with pose estimation and object detection. In this study, we introduce a novel single-stage bi-modal transformer framework for SGG in the OR, termed S2Former-OR.
  arXiv  Detail & Related papers  (2024-02-22T11:40:49Z)
• Learning Partial Correlation based Deep Visual Representation for Image Classification [61.0532370259644]
  We formulate sparse inverse covariance estimation (SICE) as a novel structured layer of CNN. Our work obtains a partial correlation based deep visual representation and mitigates the small sample problem. Experiments show the efficacy and superior classification performance of our model.
  arXiv  Detail & Related papers  (2023-04-23T10:09:01Z)
• The geometry of hidden representations of large transformer models [43.16765170255552]
  Large transformers are powerful architectures used for self-supervised data analysis across various data types. We show that the semantic structure of the dataset emerges from a sequence of transformations between one representation and the next. We show that the semantic information of the dataset is better expressed at the end of the first peak, and this phenomenon can be observed across many models trained on diverse datasets.
  arXiv  Detail & Related papers  (2023-02-01T07:50:26Z)
• FedAvg with Fine Tuning: Local Updates Lead to Representation Learning [54.65133770989836]
  Federated Averaging (FedAvg) algorithm consists of alternating between a few local gradient updates at client nodes, followed by a model averaging update at the server. We show that the reason behind generalizability of the FedAvg's output is its power in learning the common data representation among the clients' tasks. We also provide empirical evidence demonstrating FedAvg's representation learning ability in federated image classification with heterogeneous data.
  arXiv  Detail & Related papers  (2022-05-27T00:55:24Z)
• Leveraging redundancy in attention with Reuse Transformers [58.614198953733194]
  Pairwise dot product-based attention allows Transformers to exchange information between tokens in an input-dependent way. A typical Transformer model computes such pairwise attention scores repeatedly for the same sequence. We propose a novel architecture that reuses attention scores computed in one layer in multiple subsequent layers.
  arXiv  Detail & Related papers  (2021-10-13T16:08:02Z)
• No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data [78.69828864672978]
  A central challenge in training classification models in the real-world federated system is learning with non-IID data. We propose a novel and simple algorithm called Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated ssian mixture model. Experimental results demonstrate that CCVR state-of-the-art performance on popular federated learning benchmarks including CIFAR-10, CIFAR-100, and CINIC-10.
  arXiv  Detail & Related papers  (2021-06-09T12:02:29Z)
• Semantic Correspondence with Transformers [68.37049687360705]
  We propose Cost Aggregation with Transformers (CATs) to find dense correspondences between semantically similar images. We include appearance affinity modelling to disambiguate the initial correlation maps and multi-level aggregation. We conduct experiments to demonstrate the effectiveness of the proposed model over the latest methods and provide extensive ablation studies.
  arXiv  Detail & Related papers  (2021-06-04T14:39:03Z)
• Layer Reduction: Accelerating Conformer-Based Self-Supervised Model via Layer Consistency [31.572652956170252]
  Transformer-based self-supervised models are trained as feature extractors and have empowered many downstream speech tasks to achieve state-of-the-art performance. We experimentally achieve 7.8X parameter reduction, 41.9% training speedup and 37.7% inference speedup while maintaining comparable performance with conventional BERT-like self-supervised methods.
  arXiv  Detail & Related papers  (2021-04-08T08:21:59Z)
• Beyond Single Instance Multi-view Unsupervised Representation Learning [21.449132256091662]
  We impose more accurate instance discrimination capability by measuring the joint similarity between two randomly sampled instances. We believe that learning joint similarity helps to improve the performance when encoded features are distributed more evenly in the latent space.
  arXiv  Detail & Related papers  (2020-11-26T15:43:27Z)

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.