Investigating the potential of Sparse Mixtures-of-Experts for multi-domain neural machine translation

• URL: http://arxiv.org/abs/2407.01126v1
• Date: Mon, 1 Jul 2024 09:45:22 GMT
• Title: Investigating the potential of Sparse Mixtures-of-Experts for multi-domain neural machine translation
• Authors: Nadezhda Chirkova, Vassilina Nikoulina, Jean-Luc Meunier, Alexandre Bérard,
• Abstract summary: We focus on multi-domain Neural Machine Translation, with the goal of developing efficient models which can handle data from various domains seen during training and are robust to domains unseen during training. We hypothesize that Sparse Mixture-of-Experts (SMoE) models are a good fit for this task, as they enable efficient model scaling. We conduct a series of experiments aimed at validating the utility of SMoE for the multi-domain scenario, and find that a straightforward width scaling of Transformer is a simpler and surprisingly more efficient approach in practice, and reaches the same performance level as SMoE.
• Score: 59.41178047749177
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We focus on multi-domain Neural Machine Translation, with the goal of developing efficient models which can handle data from various domains seen during training and are robust to domains unseen during training. We hypothesize that Sparse Mixture-of-Experts (SMoE) models are a good fit for this task, as they enable efficient model scaling, which helps to accommodate a variety of multi-domain data, and allow flexible sharing of parameters between domains, potentially enabling knowledge transfer between similar domains and limiting negative transfer. We conduct a series of experiments aimed at validating the utility of SMoE for the multi-domain scenario, and find that a straightforward width scaling of Transformer is a simpler and surprisingly more efficient approach in practice, and reaches the same performance level as SMoE. We also search for a better recipe for robustness of multi-domain systems, highlighting the importance of mixing-in a generic domain, i.e. Paracrawl, and introducing a simple technique, domain randomization.

Related papers

• Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Counting [67.38137379297717]
  Multidomain crowd counting aims to learn a general model for multiple diverse datasets. Deep networks prefer modeling distributions of the dominant domains instead of all domains, which is known as domain bias. We propose a Modulating Domain-specific Knowledge Network (MDKNet) to handle the domain bias issue in multidomain crowd counting.
  arXiv  Detail & Related papers  (2024-02-06T06:49:04Z)
• DynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domains [26.95350186287616]
  Few-shot domain adaptation to multiple domains aims to learn a complex image distribution across multiple domains from a few training images. We propose DynaGAN, a novel few-shot domain-adaptation method for multiple target domains.
  arXiv  Detail & Related papers  (2022-11-26T12:46:40Z)
• Towards Unsupervised Domain Adaptation via Domain-Transformer [0.0]
  We propose the Domain-Transformer (DoT) for Unsupervised Domain Adaptation (UDA) DoT integrates the CNN-backbones and the core attention mechanism of Transformers from a new perspective. It achieves the local semantic consistency across domains, where the domain-level attention and manifold regularization are explored.
  arXiv  Detail & Related papers  (2022-02-24T02:30:15Z)
• A Novel Mix-normalization Method for Generalizable Multi-source Person Re-identification [49.548815417844786]
  Person re-identification (Re-ID) has achieved great success in the supervised scenario. It is difficult to directly transfer the supervised model to arbitrary unseen domains due to the model overfitting to the seen source domains. We propose MixNorm, which consists of domain-aware mix-normalization (DMN) and domain-ware center regularization (DCR)
  arXiv  Detail & Related papers  (2022-01-24T18:09:38Z)
• T-SVDNet: Exploring High-Order Prototypical Correlations for Multi-Source Domain Adaptation [41.356774580308986]
  We propose a novel approach named T-SVDNet to address the task of Multi-source Domain Adaptation. High-order correlations among multiple domains and categories are fully explored so as to better bridge the domain gap. To avoid negative transfer brought by noisy source data, we propose a novel uncertainty-aware weighting strategy.
  arXiv  Detail & Related papers  (2021-07-30T06:33:05Z)
• Multi-path Neural Networks for On-device Multi-domain Visual Classification [55.281139434736254]
  This paper proposes a novel approach to automatically learn a multi-path network for multi-domain visual classification on mobile devices. The proposed multi-path network is learned from neural architecture search by applying one reinforcement learning controller for each domain to select the best path in the super-network created from a MobileNetV3-like search space. The determined multi-path model selectively shares parameters across domains in shared nodes while keeping domain-specific parameters within non-shared nodes in individual domain paths.
  arXiv  Detail & Related papers  (2020-10-10T05:13:49Z)
• Transformer Based Multi-Source Domain Adaptation [53.24606510691877]
  In practical machine learning settings, the data on which a model must make predictions often come from a different distribution than the data it was trained on. Here, we investigate the problem of unsupervised multi-source domain adaptation, where a model is trained on labelled data from multiple source domains and must make predictions on a domain for which no labelled data has been seen. We show that the predictions of large pretrained transformer based domain experts are highly homogenous, making it challenging to learn effective functions for mixing their predictions.
  arXiv  Detail & Related papers  (2020-09-16T16:56:23Z)
• Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits [101.68525259222164]
  We present a study of various distance-based measures in the context of NLP tasks, that characterize the dissimilarity between domains based on sample estimates. We develop a DistanceNet model which uses these distance measures as an additional loss function to be minimized jointly with the task's loss function. We extend this model to a novel DistanceNet-Bandit model, which employs a multi-armed bandit controller to dynamically switch between multiple source domains.
  arXiv  Detail & Related papers  (2020-01-13T15:53:41Z)

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.