Evolving Metric Learning for Incremental and Decremental Features

• URL: http://arxiv.org/abs/2006.15334v2
• Date: Wed, 30 Jun 2021 03:21:14 GMT
• Title: Evolving Metric Learning for Incremental and Decremental Features
• Authors: Jiahua Dong, Yang Cong, Gan Sun, Tao Zhang, Xu Tang and Xiaowei Xu
• Abstract summary: We develop a new online Evolving Metric Learning model for incremental and decremental features. Our model can handle the instance and feature evolutions simultaneously by incorporating with a smoothed Wasserstein metric distance. In addition to tackling the challenges in one-shot case, we also extend our model into multishot scenario.
• Score: 45.696514400861275
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Online metric learning has been widely exploited for large-scale data classification due to the low computational cost. However, amongst online practical scenarios where the features are evolving (e.g., some features are vanished and some new features are augmented), most metric learning models cannot be successfully applied to these scenarios, although they can tackle the evolving instances efficiently. To address the challenge, we develop a new online Evolving Metric Learning (EML) model for incremental and decremental features, which can handle the instance and feature evolutions simultaneously by incorporating with a smoothed Wasserstein metric distance. Specifically, our model contains two essential stages: a Transforming stage (T-stage) and a Inheriting stage (I-stage). For the T-stage, we propose to extract important information from vanished features while neglecting non-informative knowledge, and forward it into survived features by transforming them into a low-rank discriminative metric space. It further explores the intrinsic low-rank structure of heterogeneous samples to reduce the computation and memory burden especially for highly-dimensional large-scale data. For the I-stage, we inherit the metric performance of survived features from the T-stage and then expand to include the new augmented features. Moreover, a smoothed Wasserstein distance is utilized to characterize the similarity relationships among the heterogeneous and complex samples, since the evolving features are not strictly aligned in the different stages. In addition to tackling the challenges in one-shot case, we also extend our model into multishot scenario. After deriving an efficient optimization strategy for both T-stage and I-stage, extensive experiments on several datasets verify the superior performance of our EML model.

Related papers

• Dynamic and Adaptive Feature Generation with LLM [10.142660254703225]
  We propose a dynamic and adaptive feature generation method that enhances the interpretability of the feature generation process. Our approach broadens the applicability across various data types and tasks and draws advantages over strategic flexibility.
  arXiv  Detail & Related papers  (2024-06-04T20:32:14Z)
• Online Continual Learning for Robust Indoor Object Recognition [24.316047317028143]
  Vision systems mounted on home robots need to interact with unseen classes in changing environments. We propose RobOCLe, which constructs an enriched feature space computing high order statistical moments. We show that different moments allow RobOCLe to capture different properties of deformations, providing higher robustness with no decrease of inference speed.
  arXiv  Detail & Related papers  (2023-07-19T08:32:59Z)
• To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis [50.31589712761807]
  Large language models (LLMs) are notoriously token-hungry during pre-training, and high-quality text data on the web is approaching its scaling limit for LLMs. We investigate the consequences of repeating pre-training data, revealing that the model is susceptible to overfitting. Second, we examine the key factors contributing to multi-epoch degradation, finding that significant factors include dataset size, model parameters, and training objectives.
  arXiv  Detail & Related papers  (2023-05-22T17:02:15Z)
• Theoretical Characterization of the Generalization Performance of Overfitted Meta-Learning [70.52689048213398]
  This paper studies the performance of overfitted meta-learning under a linear regression model with Gaussian features. We find new and interesting properties that do not exist in single-task linear regression. Our analysis suggests that benign overfitting is more significant and easier to observe when the noise and the diversity/fluctuation of the ground truth of each training task are large.
  arXiv  Detail & Related papers  (2023-04-09T20:36:13Z)
• Semiparametric Language Models Are Scalable Continual Learners [83.74414880208334]
  Semiparametric language models (LMs) have shown promise in continuously learning from new text data. We present a simple and intuitive approach called Selective Memorization (SeMem) SeMem only memorizes difficult samples that the model is likely to struggle with.
  arXiv  Detail & Related papers  (2023-03-02T17:15:02Z)
• Traceable Automatic Feature Transformation via Cascading Actor-Critic Agents [25.139229855367088]
  Feature transformation is an essential task to boost the effectiveness and interpretability of machine learning (ML) We formulate the feature transformation task as an iterative, nested process of feature generation and selection. We show 24.7% improvements in F1 scores compared with SOTAs and robustness in high-dimensional data.
  arXiv  Detail & Related papers  (2022-12-27T08:20:19Z)
• Efficient Feature Transformations for Discriminative and Generative Continual Learning [98.10425163678082]
  We propose a simple task-specific feature map transformation strategy for continual learning. Theses provide powerful flexibility for learning new tasks, achieved with minimal parameters added to the base architecture. We demonstrate the efficacy and efficiency of our method with an extensive set of experiments in discriminative (CIFAR-100 and ImageNet-1K) and generative sequences of tasks.
  arXiv  Detail & Related papers  (2021-03-25T01:48:14Z)
• Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning [96.75889543560497]
  In many real-world problems, collecting a large number of labeled samples is infeasible. Few-shot learning is the dominant approach to address this issue, where the objective is to quickly adapt to novel categories in presence of a limited number of samples. We propose a novel training mechanism that simultaneously enforces equivariance and invariance to a general set of geometric transformations.
  arXiv  Detail & Related papers  (2021-03-01T21:14:33Z)

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.