Hedging Is Not All You Need: A Simple Baseline for Online Learning Under Haphazard Inputs

• URL: http://arxiv.org/abs/2409.10242v1
• Date: Mon, 16 Sep 2024 12:45:03 GMT
• Title: Hedging Is Not All You Need: A Simple Baseline for Online Learning Under Haphazard Inputs
• Authors: Himanshu Buckchash, Momojit Biswas, Rohit Agarwal, Dilip K. Prasad,
• Abstract summary: HapNet is a simple baseline that is scalable, does not require online backpropagation, and is adaptable to varying input types. We demonstrate that a variant of the proposed approach can work even for this complex scenario.
• Score: 7.738999125093431
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Handling haphazard streaming data, such as data from edge devices, presents a challenging problem. Over time, the incoming data becomes inconsistent, with missing, faulty, or new inputs reappearing. Therefore, it requires models that are reliable. Recent methods to solve this problem depend on a hedging-based solution and require specialized elements like auxiliary dropouts, forked architectures, and intricate network design. We observed that hedging can be reduced to a special case of weighted residual connection; this motivated us to approximate it with plain self-attention. In this work, we propose HapNet, a simple baseline that is scalable, does not require online backpropagation, and is adaptable to varying input types. All present methods are restricted to scaling with a fixed window; however, we introduce a more complex problem of scaling with a variable window where the data becomes positionally uncorrelated, and cannot be addressed by present methods. We demonstrate that a variant of the proposed approach can work even for this complex scenario. We extensively evaluated the proposed approach on five benchmarks and found competitive performance.

Related papers

• Symmetry-preserving graph attention network to solve routing problems at multiple resolutions [1.9304772860080408]
  We introduce the first-ever completely equivariant model and training to solve problems. It is essential to capture the multiscale structure of the input graph. We propose a Multiresolution scheme in combination with Equi Graph Attention network (mEGAT) architecture.
  arXiv  Detail & Related papers  (2023-10-24T06:22:20Z)
• Informative Data Mining for One-Shot Cross-Domain Semantic Segmentation [84.82153655786183]
  We propose a novel framework called Informative Data Mining (IDM) to enable efficient one-shot domain adaptation for semantic segmentation. IDM provides an uncertainty-based selection criterion to identify the most informative samples, which facilitates quick adaptation and reduces redundant training. Our approach outperforms existing methods and achieves a new state-of-the-art one-shot performance of 56.7%/55.4% on the GTA5/SYNTHIA to Cityscapes adaptation tasks.
  arXiv  Detail & Related papers  (2023-09-25T15:56:01Z)
• Discrete Key-Value Bottleneck [95.61236311369821]
  Deep neural networks perform well on classification tasks where data streams are i.i.d. and labeled data is abundant. One powerful approach that has addressed this challenge involves pre-training of large encoders on volumes of readily available data, followed by task-specific tuning. Given a new task, however, updating the weights of these encoders is challenging as a large number of weights needs to be fine-tuned, and as a result, they forget information about the previous tasks. We propose a model architecture to address this issue, building upon a discrete bottleneck containing pairs of separate and learnable key-value codes.
  arXiv  Detail & Related papers  (2022-07-22T17:52:30Z)
• DeepSplit: Scalable Verification of Deep Neural Networks via Operator Splitting [70.62923754433461]
  Analyzing the worst-case performance of deep neural networks against input perturbations amounts to solving a large-scale non- optimization problem. We propose a novel method that can directly solve a convex relaxation of the problem to high accuracy, by splitting it into smaller subproblems that often have analytical solutions.
  arXiv  Detail & Related papers  (2021-06-16T20:43:49Z)
• Mixed-Privacy Forgetting in Deep Networks [114.3840147070712]
  We show that the influence of a subset of the training samples can be removed from the weights of a network trained on large-scale image classification tasks. Inspired by real-world applications of forgetting techniques, we introduce a novel notion of forgetting in mixed-privacy setting. We show that our method allows forgetting without having to trade off the model accuracy.
  arXiv  Detail & Related papers  (2020-12-24T19:34:56Z)
• Deep Magnification-Flexible Upsampling over 3D Point Clouds [103.09504572409449]
  We propose a novel end-to-end learning-based framework to generate dense point clouds. We first formulate the problem explicitly, which boils down to determining the weights and high-order approximation errors. Then, we design a lightweight neural network to adaptively learn unified and sorted weights as well as the high-order refinements.
  arXiv  Detail & Related papers  (2020-11-25T14:00:18Z)
• Low-Rank Robust Online Distance/Similarity Learning based on the Rescaled Hinge Loss [0.34376560669160383]
  Existing online methods usually assume training triplets or pairwise constraints are exist in advance. We formulate the online Distance-Similarity learning problem with the robust Rescaled hinge loss function. The proposed model is rather general and can be applied to any PA-based online Distance-Similarity algorithm.
  arXiv  Detail & Related papers  (2020-10-07T08:38:34Z)
• Instance exploitation for learning temporary concepts from sparsely labeled drifting data streams [15.49323098362628]
  Continual learning from streaming data sources becomes more and more popular. dealing with dynamic and everlasting problems poses new challenges. One of the most crucial limitations is that we cannot assume having access to a finite and complete data set.
  arXiv  Detail & Related papers  (2020-09-20T08:11:43Z)
• Differentiable Causal Discovery from Interventional Data [141.41931444927184]
  We propose a theoretically-grounded method based on neural networks that can leverage interventional data. We show that our approach compares favorably to the state of the art in a variety of settings.
  arXiv  Detail & Related papers  (2020-07-03T15:19:17Z)

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.