Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning

• URL: http://arxiv.org/abs/2501.15556v1
• Date: Sun, 26 Jan 2025 15:12:06 GMT
• Title: Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning
• Authors: Alexey Rukhovich, Alexander Podolskiy, Irina Piontkovskaya,
• Abstract summary: In multi-domain learning, a single model is trained on diverse data domains to leverage shared knowledge and improve generalization. The order in which the data from these domains is used for training can significantly affect the model's performance on each domain. We investigate the influence of training order (or data mixing) in multi-domain learning using the concept of Lie bracket of gradient vector fields.
• Score: 50.80758278865274
• License:
• Abstract: In multi-domain learning, a single model is trained on diverse data domains to leverage shared knowledge and improve generalization. The order in which the data from these domains is used for training can significantly affect the model's performance on each domain. However, this dependence is under-studied. In this paper, we investigate the influence of training order (or data mixing) in multi-domain learning using the concept of Lie bracket of gradient vector fields. By analyzing the infinitesimal effects of changing the training order, we identify regions in the parameter space where altering the order between two training domains can benefit the target loss. We validate the predictions of our theoretical framework on the influence of training order (or data mixing) both on a toy example and bilingual LLM pre-training.

Related papers

• DoGE: Domain Reweighting with Generalization Estimation [42.32000165235568]
  We propose DOmain reweighting with Generalization Estimation (DoGE) In our experiments, we extensively show how DoGE improves the generalization of the base model to any target data mixture. DoGE can effectively identify inter-domain dependencies, and consistently achieves better test perplexity on the target domain.
  arXiv  Detail & Related papers  (2023-10-23T22:51:58Z)
• Improving Domain Generalization with Domain Relations [77.63345406973097]
  This paper focuses on domain shifts, which occur when the model is applied to new domains that are different from the ones it was trained on. We propose a new approach called D$3$G to learn domain-specific models. Our results show that D$3$G consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-02-06T08:11:16Z)
• Efficient Hierarchical Domain Adaptation for Pretrained Language Models [77.02962815423658]
  Generative language models are trained on diverse, general domain corpora. We introduce a method to scale domain adaptation to many diverse domains using a computationally efficient adapter approach.
  arXiv  Detail & Related papers  (2021-12-16T11:09:29Z)
• Domain Generalization via Gradient Surgery [5.38147998080533]
  In real-life applications, machine learning models often face scenarios where there is a change in data distribution between training and test domains. In this work, we characterize the conflicting gradients emerging in domain shift scenarios and devise novel gradient agreement strategies.
  arXiv  Detail & Related papers  (2021-08-03T16:49:25Z)
• Batch Normalization Embeddings for Deep Domain Generalization [50.51405390150066]
  Domain generalization aims at training machine learning models to perform robustly across different and unseen domains. We show a significant increase in classification accuracy over current state-of-the-art techniques on popular domain generalization benchmarks.
  arXiv  Detail & Related papers  (2020-11-25T12:02:57Z)
• A Brief Review of Domain Adaptation [1.2043574473965317]
  This paper focuses on unsupervised domain adaptation, where the labels are only available in the source domain. It presents some successful shallow and deep domain adaptation approaches that aim to deal with domain adaptation problems.
  arXiv  Detail & Related papers  (2020-10-07T07:05:32Z)
• Domain Adaptation for Semantic Parsing [68.81787666086554]
  We propose a novel semantic for domain adaptation, where we have much fewer annotated data in the target domain compared to the source domain. Our semantic benefits from a two-stage coarse-to-fine framework, thus can provide different and accurate treatments for the two stages. Experiments on a benchmark dataset show that our method consistently outperforms several popular domain adaptation strategies.
  arXiv  Detail & Related papers  (2020-06-23T14:47:41Z)
• Multi-Domain Spoken Language Understanding Using Domain- and Task-Aware Parameterization [78.93669377251396]
  Spoken language understanding has been addressed as a supervised learning problem, where a set of training data is available for each domain. One existing approach solves the problem by conducting multi-domain learning, using shared parameters for joint training across domains. We propose to improve the parameterization of this method by using domain-specific and task-specific model parameters.
  arXiv  Detail & Related papers  (2020-04-30T15:15:40Z)

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.