Improving Distribution Alignment with Diversity-based Sampling
- URL: http://arxiv.org/abs/2410.04235v1
- Date: Sat, 5 Oct 2024 17:26:03 GMT
- Title: Improving Distribution Alignment with Diversity-based Sampling
- Authors: Andrea Napoli, Paul White,
- Abstract summary: Domain shifts are ubiquitous in machine learning, and can substantially degrade a model's performance when deployed to real-world data.
This paper proposes to improve these estimates by inducing diversity in each sampled minibatch.
It simultaneously balances the data and reduces the variance of the gradients, thereby enhancing the model's generalisation ability.
- Score: 0.0
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Domain shifts are ubiquitous in machine learning, and can substantially degrade a model's performance when deployed to real-world data. To address this, distribution alignment methods aim to learn feature representations which are invariant across domains, by minimising the discrepancy between the distributions. However, the discrepancy estimates can be extremely noisy when training via stochastic gradient descent (SGD), and shifts in the relative proportions of different subgroups can lead to domain misalignments; these can both stifle the benefits of the method. This paper proposes to improve these estimates by inducing diversity in each sampled minibatch. This simultaneously balances the data and reduces the variance of the gradients, thereby enhancing the model's generalisation ability. We describe two options for diversity-based data samplers, based on the k-determinantal point process (k-DPP) and the k-means++ algorithm, which can function as drop-in replacements for a standard random sampler. On a real-world domain shift task of bioacoustic event detection, we show that both options 1) yield minibatches which are more representative of the full dataset; 2) reduce the distance estimation error between distributions, for a given sample size; and 3) improve out-of-distribution accuracy for two distribution alignment algorithms, as well as standard ERM.
Related papers
- Reducing Semantic Ambiguity In Domain Adaptive Semantic Segmentation Via Probabilistic Prototypical Pixel Contrast [7.092718945468069]
Domain adaptation aims to reduce the model degradation on the target domain caused by the domain shift between the source and target domains.
Probabilistic proto-typical pixel contrast (PPPC) is a universal adaptation framework that models each pixel embedding as a probability.
PPPC not only helps to address ambiguity at the pixel level, yielding discriminative representations but also significant improvements in both synthetic-to-real and day-to-night adaptation tasks.
arXiv Detail & Related papers (2024-09-27T08:25:03Z) - Collaborative Heterogeneous Causal Inference Beyond Meta-analysis [68.4474531911361]
We propose a collaborative inverse propensity score estimator for causal inference with heterogeneous data.
Our method shows significant improvements over the methods based on meta-analysis when heterogeneity increases.
arXiv Detail & Related papers (2024-04-24T09:04:36Z) - Deep Generative Sampling in the Dual Divergence Space: A Data-efficient & Interpretative Approach for Generative AI [29.13807697733638]
We build on the remarkable achievements in generative sampling of natural images.
We propose an innovative challenge, potentially overly ambitious, which involves generating samples that resemble images.
The statistical challenge lies in the small sample size, sometimes consisting of a few hundred subjects.
arXiv Detail & Related papers (2024-04-10T22:35:06Z) - Invariant Anomaly Detection under Distribution Shifts: A Causal
Perspective [6.845698872290768]
Anomaly detection (AD) is the machine learning task of identifying highly discrepant abnormal samples.
Under the constraints of a distribution shift, the assumption that training samples and test samples are drawn from the same distribution breaks down.
We attempt to increase the resilience of anomaly detection models to different kinds of distribution shifts.
arXiv Detail & Related papers (2023-12-21T23:20:47Z) - Divide and Contrast: Source-free Domain Adaptation via Adaptive
Contrastive Learning [122.62311703151215]
Divide and Contrast (DaC) aims to connect the good ends of both worlds while bypassing their limitations.
DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals.
We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch.
arXiv Detail & Related papers (2022-11-12T09:21:49Z) - A Unified Framework for Multi-distribution Density Ratio Estimation [101.67420298343512]
Binary density ratio estimation (DRE) provides the foundation for many state-of-the-art machine learning algorithms.
We develop a general framework from the perspective of Bregman minimization divergence.
We show that our framework leads to methods that strictly generalize their counterparts in binary DRE.
arXiv Detail & Related papers (2021-12-07T01:23:20Z) - Learning Invariant Representations and Risks for Semi-supervised Domain
Adaptation [109.73983088432364]
We propose the first method that aims to simultaneously learn invariant representations and risks under the setting of semi-supervised domain adaptation (Semi-DA)
We introduce the LIRR algorithm for jointly textbfLearning textbfInvariant textbfRepresentations and textbfRisks.
arXiv Detail & Related papers (2020-10-09T15:42:35Z) - The Bures Metric for Generative Adversarial Networks [10.69910379275607]
Generative Adversarial Networks (GANs) are performant generative methods yielding high-quality samples.
We propose to match the real batch diversity to the fake batch diversity.
We observe that diversity matching reduces mode collapse substantially and has a positive effect on the sample quality.
arXiv Detail & Related papers (2020-06-16T12:04:41Z) - Global Distance-distributions Separation for Unsupervised Person
Re-identification [93.39253443415392]
Existing unsupervised ReID approaches often fail in correctly identifying the positive samples and negative samples through the distance-based matching/ranking.
We introduce a global distance-distributions separation constraint over the two distributions to encourage the clear separation of positive and negative samples from a global view.
We show that our method leads to significant improvement over the baselines and achieves the state-of-the-art performance.
arXiv Detail & Related papers (2020-06-01T07:05:39Z) - Spatially Adaptive Inference with Stochastic Feature Sampling and
Interpolation [72.40827239394565]
We propose to compute features only at sparsely sampled locations.
We then densely reconstruct the feature map with an efficient procedure.
The presented network is experimentally shown to save substantial computation while maintaining accuracy over a variety of computer vision tasks.
arXiv Detail & Related papers (2020-03-19T15:36:31Z)
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.