Understanding Out-of-distribution: A Perspective of Data Dynamics

• URL: http://arxiv.org/abs/2111.14730v1
• Date: Mon, 29 Nov 2021 17:34:38 GMT
• Title: Understanding Out-of-distribution: A Perspective of Data Dynamics
• Authors: Dyah Adila and Dongyeop Kang
• Abstract summary: This paper explores how data dynamics in training models can be used to understand the fundamental differences between OOD and in-distribution samples. We found that syntactic characteristics of the data samples that the model consistently predicts incorrectly in both OOD and in-distribution cases directly contradict each.
• Score: 5.811774625668462
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite machine learning models' success in Natural Language Processing (NLP) tasks, predictions from these models frequently fail on out-of-distribution (OOD) samples. Prior works have focused on developing state-of-the-art methods for detecting OOD. The fundamental question of how OOD samples differ from in-distribution samples remains unanswered. This paper explores how data dynamics in training models can be used to understand the fundamental differences between OOD and in-distribution samples in extensive detail. We found that syntactic characteristics of the data samples that the model consistently predicts incorrectly in both OOD and in-distribution cases directly contradict each other. In addition, we observed preliminary evidence supporting the hypothesis that models are more likely to latch on trivial syntactic heuristics (e.g., overlap of words between two sentences) when making predictions on OOD samples. We hope our preliminary study accelerates the data-centric analysis on various machine learning phenomena.

Related papers

• Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation [53.27596811146316]
  Diffusion models operate over a sequence of timesteps instead of instantaneous input-output relationships in previous contexts. We present Diffusion-TracIn that incorporates this temporal dynamics and observe that samples' loss gradient norms are highly dependent on timestep. We introduce Diffusion-ReTrac as a re-normalized adaptation that enables the retrieval of training samples more targeted to the test sample of interest.
  arXiv  Detail & Related papers  (2024-01-17T07:58:18Z)
• Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models [3.9052860539161918]
  We propose a simple method for measuring a scale of models' reliance on any identified spurious feature. We assess the robustness towards a large set of known and newly found prediction biases for various pre-trained models and debiasing methods in Question Answering (QA) We find that while existing debiasing methods can mitigate reliance on a chosen spurious feature, the OOD performance gains of these methods can not be explained by mitigated reliance on biased features.
  arXiv  Detail & Related papers  (2023-05-11T14:35:00Z)
• Pseudo-OOD training for robust language models [78.15712542481859]
  OOD detection is a key component of a reliable machine-learning model for any industry-scale application. We propose POORE - POsthoc pseudo-Ood REgularization, that generates pseudo-OOD samples using in-distribution (IND) data. We extensively evaluate our framework on three real-world dialogue systems, achieving new state-of-the-art in OOD detection.
  arXiv  Detail & Related papers  (2022-10-17T14:32:02Z)
• Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning [54.61762276179205]
  We propose a novel contrastive learning approach, MMBS, for building robust VQA models by Making the Most of Biased Samples. Specifically, we construct positive samples for contrastive learning by eliminating the information related to spurious correlation from the original training samples. We validate our contributions by achieving competitive performance on the OOD dataset VQA-CP v2 while preserving robust performance on the ID dataset VQA v2.
  arXiv  Detail & Related papers  (2022-10-10T11:05:21Z)
• Pathologies of Pre-trained Language Models in Few-shot Fine-tuning [50.3686606679048]
  We show that pre-trained language models with few examples show strong prediction bias across labels. Although few-shot fine-tuning can mitigate the prediction bias, our analysis shows models gain performance improvement by capturing non-task-related features. These observations alert that pursuing model performance with fewer examples may incur pathological prediction behavior.
  arXiv  Detail & Related papers  (2022-04-17T15:55:18Z)
• Understanding, Detecting, and Separating Out-of-Distribution Samples and Adversarial Samples in Text Classification [80.81532239566992]
  We compare the two types of anomalies (OOD and Adv samples) with the in-distribution (ID) ones from three aspects. We find that OOD samples expose their aberration starting from the first layer, while the abnormalities of Adv samples do not emerge until the deeper layers of the model. We propose a simple method to separate ID, OOD, and Adv samples using the hidden representations and output probabilities of the model.
  arXiv  Detail & Related papers  (2022-04-09T12:11:59Z)
• Understanding and Testing Generalization of Deep Networks on Out-of-Distribution Data [30.471871571256198]
  Deep network models perform excellently on In-Distribution data, but can significantly fail on Out-Of-Distribution data. This study is devoted to analyzing the problem of experimental ID test and designing OOD test paradigm.
  arXiv  Detail & Related papers  (2021-11-17T15:29:07Z)
• Learn what you can't learn: Regularized Ensembles for Transductive Out-of-distribution Detection [76.39067237772286]
  We show that current out-of-distribution (OOD) detection algorithms for neural networks produce unsatisfactory results in a variety of OOD detection scenarios. This paper studies how such "hard" OOD scenarios can benefit from adjusting the detection method after observing a batch of the test data. We propose a novel method that uses an artificial labeling scheme for the test data and regularization to obtain ensembles of models that produce contradictory predictions only on the OOD samples in a test batch.
  arXiv  Detail & Related papers  (2020-12-10T16:55:13Z)
• Out-of-distribution detection for regression tasks: parameter versus predictor entropy [2.026281591452464]
  It is crucial to detect when an instance lies downright too far from the training samples for the machine learning model to be trusted. For neural networks, one approach to this task consists of learning a diversity of predictors that all can explain the training data. We propose a new way of estimating the entropy of a distribution on predictors based on nearest neighbors in function space.
  arXiv  Detail & Related papers  (2020-10-24T21:41:21Z)

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.