On Sensitivity of Learning with Limited Labelled Data to the Effects of Randomness: Impact of Interactions and Systematic Choices

• URL: http://arxiv.org/abs/2402.12817v1
• Date: Tue, 20 Feb 2024 08:38:19 GMT
• Title: On Sensitivity of Learning with Limited Labelled Data to the Effects of Randomness: Impact of Interactions and Systematic Choices
• Authors: Branislav Pecher, Ivan Srba, Maria Bielikova
• Abstract summary: We propose a method to investigate the effects of randomness factors while taking the interactions into consideration. To measure the true effects of an individual randomness factor, our method mitigates the effects of other factors and observes how the performance varies across multiple runs. Applying our method to multiple randomness factors across in-context learning and fine-tuning approaches on 7 representative text classification tasks and meta-learning on 3 tasks, we show that: 1) disregarding interactions between randomness factors in existing works caused inconsistent findings due to incorrect attribution of the effects of randomness factors, such as disproving the consistent sensitivity of in-context learning to sample order even
• Score: 5.630038762653309
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While learning with limited labelled data can improve performance when the labels are lacking, it is also sensitive to the effects of uncontrolled randomness introduced by so-called randomness factors (e.g., varying order of data). We propose a method to systematically investigate the effects of randomness factors while taking the interactions between them into consideration. To measure the true effects of an individual randomness factor, our method mitigates the effects of other factors and observes how the performance varies across multiple runs. Applying our method to multiple randomness factors across in-context learning and fine-tuning approaches on 7 representative text classification tasks and meta-learning on 3 tasks, we show that: 1) disregarding interactions between randomness factors in existing works caused inconsistent findings due to incorrect attribution of the effects of randomness factors, such as disproving the consistent sensitivity of in-context learning to sample order even with random sample selection; and 2) besides mutual interactions, the effects of randomness factors, especially sample order, are also dependent on more systematic choices unexplored in existing works, such as number of classes, samples per class or choice of prompt format.

Related papers

• On the Effects of Randomness on Stability of Learning with Limited Labelled Data: A Systematic Literature Review [5.630038762653309]
  This paper provides a comprehensive overview of 134 papers addressing the effects of randomness on the stability of learning with limited labelled data. We identify and discuss seven challenges and open problems together with possible directions to facilitate further research.
  arXiv  Detail & Related papers  (2023-12-02T09:20:10Z)
• Causal Inference from Text: Unveiling Interactions between Variables [20.677407402398405]
  Existing methods only account for confounding covariables that affect both treatment and outcome. This bias arises from insufficient consideration of non-confounding covariables. In this work, we aim to mitigate the bias by unveiling interactions between different variables.
  arXiv  Detail & Related papers  (2023-11-09T11:29:44Z)
• Causal Feature Selection via Transfer Entropy [59.999594949050596]
  Causal discovery aims to identify causal relationships between features with observational data. We introduce a new causal feature selection approach that relies on the forward and backward feature selection procedures. We provide theoretical guarantees on the regression and classification errors for both the exact and the finite-sample cases.
  arXiv  Detail & Related papers  (2023-10-17T08:04:45Z)
• Fair Effect Attribution in Parallel Online Experiments [57.13281584606437]
  A/B tests serve the purpose of reliably identifying the effect of changes introduced in online services. It is common for online platforms to run a large number of simultaneous experiments by splitting incoming user traffic randomly. Despite a perfect randomization between different groups, simultaneous experiments can interact with each other and create a negative impact on average population outcomes.
  arXiv  Detail & Related papers  (2022-10-15T17:15:51Z)
• Valid Inference after Causal Discovery [95.20382312836541]
  We develop tools for valid post-causal-discovery inference. We show that a naive combination of causal discovery and subsequent inference algorithms leads to highly inflated miscoverage rates.
  arXiv  Detail & Related papers  (2022-08-11T17:40:45Z)
• SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data [83.50281440043241]
  We study the problem of inferring heterogeneous treatment effects from time-to-event data. We propose a novel deep learning method for treatment-specific hazard estimation based on balancing representations.
  arXiv  Detail & Related papers  (2021-10-26T20:13:17Z)
• Impact of Spatial Frequency Based Constraints on Adversarial Robustness [0.49478969093606673]
  Adversarial examples mainly exploit changes to input pixels to which humans are not sensitive, and arise from the fact that models make decisions based on uninterpretable features. In this paper, we investigate the robustness to adversarial perturbations of models enforced during training to leverage information corresponding to different spatial frequency ranges.
  arXiv  Detail & Related papers  (2021-04-26T16:12:04Z)
• Precise High-Dimensional Asymptotics for Quantifying Heterogeneous Transfers [34.40702005466919]
  When is combining data from two tasks better than learning one task alone? This paper uses random matrix theory to tackle this challenge in a linear regression setting with two tasks.
  arXiv  Detail & Related papers  (2020-10-22T14:14:20Z)
• Hidden Cost of Randomized Smoothing [72.93630656906599]
  In this paper, we point out the side effects of current randomized smoothing. Specifically, we articulate and prove two major points: 1) the decision boundaries of smoothed classifiers will shrink, resulting in disparity in class-wise accuracy; 2) applying noise augmentation in the training process does not necessarily resolve the shrinking issue due to the inconsistent learning objectives.
  arXiv  Detail & Related papers  (2020-03-02T23:37:42Z)
• Improving Multi-Turn Response Selection Models with Complementary Last-Utterance Selection by Instance Weighting [84.9716460244444]
  We consider utilizing the underlying correlation in the data resource itself to derive different kinds of supervision signals. We conduct extensive experiments in two public datasets and obtain significant improvement in both datasets.
  arXiv  Detail & Related papers  (2020-02-18T06:29:01Z)
• Treatment effect estimation with disentangled latent factors [24.803992990503186]
  We show the importance of differentiating confounding factors from instrumental and risk factors for both average and conditional average treatment effect estimation. We propose a variational inference approach to simultaneously infer latent factors from the observed variables, disentangle the factors into three disjoint sets corresponding to the instrumental, confounding, and risk factors, and use the disentangled factors for treatment effect estimation.
  arXiv  Detail & Related papers  (2020-01-29T01:00:36Z)

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.