SiameseDuo++: Active Learning from Data Streams with Dual Augmented Siamese Networks

• URL: http://arxiv.org/abs/2504.04613v1
• Date: Sun, 06 Apr 2025 20:45:25 GMT
• Title: SiameseDuo++: Active Learning from Data Streams with Dual Augmented Siamese Networks
• Authors: Kleanthis Malialis, Stylianos Filippou, Christos G. Panayiotou, Marios M. Polycarpou,
• Abstract summary: This work proposes the SiameseDuo++ method, which uses active learning to automatically select instances for a human expert to label according to a budget.<n>Specifically, it incrementally trains two siamese neural networks which operate in synergy, augmented by generated examples.<n> Simulation experiments show that the proposed method outperforms strong baselines and state-of-the-art methods in terms of learning speed and/or performance.
• Score: 8.762175520727611
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Data stream mining, also known as stream learning, is a growing area which deals with learning from high-speed arriving data. Its relevance has surged recently due to its wide range of applicability, such as, critical infrastructure monitoring, social media analysis, and recommender systems. The design of stream learning methods faces significant research challenges; from the nonstationary nature of the data (referred to as concept drift) and the fact that data streams are typically not annotated with the ground truth, to the requirement that such methods should process large amounts of data in real-time with limited memory. This work proposes the SiameseDuo++ method, which uses active learning to automatically select instances for a human expert to label according to a budget. Specifically, it incrementally trains two siamese neural networks which operate in synergy, augmented by generated examples. Both the proposed active learning strategy and augmentation operate in the latent space. SiameseDuo++ addresses the aforementioned challenges by operating with limited memory and limited labelling budget. Simulation experiments show that the proposed method outperforms strong baselines and state-of-the-art methods in terms of learning speed and/or performance. To promote open science we publicly release our code and datasets.

Related papers

• A Survey of Label-Efficient Deep Learning for 3D Point Clouds [109.07889215814589]
  This paper presents the first comprehensive survey of label-efficient learning of point clouds. We propose a taxonomy that organizes label-efficient learning methods based on the data prerequisites provided by different types of labels. For each approach, we outline the problem setup and provide an extensive literature review that showcases relevant progress and challenges.
  arXiv  Detail & Related papers  (2023-05-31T12:54:51Z)
• Reinforcement Learning from Passive Data via Latent Intentions [86.4969514480008]
  We show that passive data can still be used to learn features that accelerate downstream RL. Our approach learns from passive data by modeling intentions. Our experiments demonstrate the ability to learn from many forms of passive data, including cross-embodiment video data and YouTube videos.
  arXiv  Detail & Related papers  (2023-04-10T17:59:05Z)
• Learning and Retrieval from Prior Data for Skill-based Imitation Learning [47.59794569496233]
  We develop a skill-based imitation learning framework that extracts temporally extended sensorimotor skills from prior data. We identify several key design choices that significantly improve performance on novel tasks.
  arXiv  Detail & Related papers  (2022-10-20T17:34:59Z)
• Data augmentation on-the-fly and active learning in data stream classification [9.367903089535684]
  There is an emerging need for predictive models to be trained on-the-fly. Learning models have access to more labelled data without the need to increase the active learning budget. Augmented Queues significantly improves the performance in terms of learning quality and speed.
  arXiv  Detail & Related papers  (2022-10-13T09:57:08Z)
• Nonstationary data stream classification with online active learning and siamese neural networks [11.501721946030779]
  An emerging need for online learning methods that train predictive models on-the-fly. A series of open challenges, however, hinder their deployment in practice. We propose the ActiSiamese algorithm, which addresses these challenges by combining online active learning, siamese networks, and a multi-queue memory.
  arXiv  Detail & Related papers  (2022-10-03T17:16:03Z)
• Transfer Learning with Deep Tabular Models [66.67017691983182]
  We show that upstream data gives tabular neural networks a decisive advantage over GBDT models. We propose a realistic medical diagnosis benchmark for tabular transfer learning. We propose a pseudo-feature method for cases where the upstream and downstream feature sets differ.
  arXiv  Detail & Related papers  (2022-06-30T14:24:32Z)
• Self-Supervised Graph Neural Network for Multi-Source Domain Adaptation [51.21190751266442]
  Domain adaptation (DA) tries to tackle the scenarios when the test data does not fully follow the same distribution of the training data. By learning from large-scale unlabeled samples, self-supervised learning has now become a new trend in deep learning. We propose a novel textbfSelf-textbfSupervised textbfGraph Neural Network (SSG) to enable more effective inter-task information exchange and knowledge sharing.
  arXiv  Detail & Related papers  (2022-04-08T03:37:56Z)
• Improved Speech Emotion Recognition using Transfer Learning and Spectrogram Augmentation [56.264157127549446]
  Speech emotion recognition (SER) is a challenging task that plays a crucial role in natural human-computer interaction. One of the main challenges in SER is data scarcity. We propose a transfer learning strategy combined with spectrogram augmentation.
  arXiv  Detail & Related papers  (2021-08-05T10:39:39Z)
• Graph-based Reinforcement Learning for Active Learning in Real Time: An Application in Modeling River Networks [2.8631830115500394]
  We develop a real-time active learning method that uses the spatial and temporal contextual information to select representative query samples in a reinforcement learning framework. We demonstrate the effectiveness of the proposed method by predicting streamflow and water temperature in the Delaware River Basin given a limited budget for collecting labeled data.
  arXiv  Detail & Related papers  (2020-10-27T02:19:40Z)
• Continual Prototype Evolution: Learning Online from Non-Stationary Data Streams [42.525141660788]
  We introduce a system to enable learning and prediction at any point in time. In contrast to the major body of work in continual learning, data streams are processed in an online fashion. We obtain state-of-the-art performance by a significant margin on eight benchmarks, including three highly imbalanced data streams.
  arXiv  Detail & Related papers  (2020-09-02T09:39:26Z)

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.