Constraint Guided Gradient Descent: Guided Training with Inequality Constraints

• URL: http://arxiv.org/abs/2206.06202v2
• Date: Tue, 14 Jun 2022 06:01:03 GMT
• Title: Constraint Guided Gradient Descent: Guided Training with Inequality Constraints
• Authors: Quinten Van Baelen, Peter Karsmakers
• Abstract summary: Constraint Guided Gradient Descent (CGGD) is proposed that enables the injection of domain knowledge into the training procedure. CGGD converges to a model that satisfies any inequality constraint on the training data. It is empirically shown on two independent and small data sets that CGGD makes training less dependent on the initialisation of the network.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning is typically performed by learning a neural network solely from data in the form of input-output pairs ignoring available domain knowledge. In this work, the Constraint Guided Gradient Descent (CGGD) framework is proposed that enables the injection of domain knowledge into the training procedure. The domain knowledge is assumed to be described as a conjunction of hard inequality constraints which appears to be a natural choice for several applications. Compared to other neuro-symbolic approaches, the proposed method converges to a model that satisfies any inequality constraint on the training data and does not require to first transform the constraints into some ad-hoc term that is added to the learning (optimisation) objective. Under certain conditions, it is shown that CGGD can converges to a model that satisfies the constraints on the training set, while prior work does not necessarily converge to such a model. It is empirically shown on two independent and small data sets that CGGD makes training less dependent on the initialisation of the network and improves the constraint satisfiability on all data.

Related papers

• DiffClass: Diffusion-Based Class Incremental Learning [30.514281721324853]
  Class Incremental Learning (CIL) is challenging due to catastrophic forgetting. Recent exemplar-free CIL methods attempt to mitigate catastrophic forgetting by synthesizing previous task data. We propose a novel exemplar-free CIL method to overcome these issues.
  arXiv  Detail & Related papers  (2024-03-08T03:34:18Z)
• Deep Neural Network for Constraint Acquisition through Tailored Loss Function [0.0]
  The significance of learning constraints from data is underscored by its potential applications in real-world problem-solving. This work introduces a novel approach grounded in Deep Neural Network (DNN) based on Symbolic Regression.
  arXiv  Detail & Related papers  (2024-03-04T13:47:33Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)
• Regularized Conditional Alignment for Multi-Domain Text Classification [6.629561563470492]
  We propose a method called Regularized Conditional Alignment (RCA) to align the joint distributions of domains and classes. We employ entropy minimization and virtual adversarial training to constrain the uncertainty of predictions pertaining to unlabeled data. Empirical results on two benchmark datasets demonstrate that our RCA approach outperforms state-of-the-art MDTC techniques.
  arXiv  Detail & Related papers  (2023-12-18T05:52:05Z)
• Neural Fields with Hard Constraints of Arbitrary Differential Order [61.49418682745144]
  We develop a series of approaches for enforcing hard constraints on neural fields. The constraints can be specified as a linear operator applied to the neural field and its derivatives. Our approaches are demonstrated in a wide range of real-world applications.
  arXiv  Detail & Related papers  (2023-06-15T08:33:52Z)
• CONDA: Continual Unsupervised Domain Adaptation Learning in Visual Perception for Self-Driving Cars [11.479857808195774]
  We propose a Continual Unsupervised Domain Adaptation (CONDA) approach that allows the model to continuously learn and adapt with respect to the presence of the new data. To avoid the catastrophic forgetting problem and maintain the performance of the segmentation models, we present a novel Bijective Maximum Likelihood loss.
  arXiv  Detail & Related papers  (2022-12-01T16:15:54Z)
• A Curriculum-style Self-training Approach for Source-Free Semantic Segmentation [91.13472029666312]
  We propose a curriculum-style self-training approach for source-free domain adaptive semantic segmentation. Our method yields state-of-the-art performance on source-free semantic segmentation tasks for both synthetic-to-real and adverse conditions.
  arXiv  Detail & Related papers  (2021-06-22T10:21:39Z)
• Developing Constrained Neural Units Over Time [81.19349325749037]
  This paper focuses on an alternative way of defining Neural Networks, that is different from the majority of existing approaches. The structure of the neural architecture is defined by means of a special class of constraints that are extended also to the interaction with data. The proposed theory is cast into the time domain, in which data are presented to the network in an ordered manner.
  arXiv  Detail & Related papers  (2020-09-01T09:07:25Z)
• 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)
• Universal Source-Free Domain Adaptation [57.37520645827318]
  We propose a novel two-stage learning process for domain adaptation. In the Procurement stage, we aim to equip the model for future source-free deployment, assuming no prior knowledge of the upcoming category-gap and domain-shift. In the Deployment stage, the goal is to design a unified adaptation algorithm capable of operating across a wide range of category-gaps.
  arXiv  Detail & Related papers  (2020-04-09T07:26:20Z)

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.