On the Impact of Temporal Concept Drift on Model Explanations

• URL: http://arxiv.org/abs/2210.09197v1
• Date: Mon, 17 Oct 2022 15:53:09 GMT
• Title: On the Impact of Temporal Concept Drift on Model Explanations
• Authors: Zhixue Zhao, George Chrysostomou, Kalina Bontcheva, Nikolaos Aletras
• Abstract summary: Explanation faithfulness of model predictions in natural language processing is evaluated on held-out data from the same temporal distribution as the training data. We examine the impact of temporal variation on model explanations extracted by eight feature attribution methods and three select-then-predict models across six text classification tasks.
• Score: 31.390397997989712
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Explanation faithfulness of model predictions in natural language processing is typically evaluated on held-out data from the same temporal distribution as the training data (i.e. synchronous settings). While model performance often deteriorates due to temporal variation (i.e. temporal concept drift), it is currently unknown how explanation faithfulness is impacted when the time span of the target data is different from the data used to train the model (i.e. asynchronous settings). For this purpose, we examine the impact of temporal variation on model explanations extracted by eight feature attribution methods and three select-then-predict models across six text classification tasks. Our experiments show that (i)faithfulness is not consistent under temporal variations across feature attribution methods (e.g. it decreases or increases depending on the method), with an attention-based method demonstrating the most robust faithfulness scores across datasets; and (ii) select-then-predict models are mostly robust in asynchronous settings with only small degradation in predictive performance. Finally, feature attribution methods show conflicting behavior when used in FRESH (i.e. a select-and-predict model) and for measuring sufficiency/comprehensiveness (i.e. as post-hoc methods), suggesting that we need more robust metrics to evaluate post-hoc explanation faithfulness.

Related papers

• TimeInf: Time Series Data Contribution via Influence Functions [8.018453062120916]
  TimeInf is a data contribution estimation method for time-series datasets. Our empirical results demonstrate that TimeInf outperforms state-of-the-art methods in identifying harmful anomalies. TimeInf offers intuitive and interpretable attributions of data values, allowing us to easily distinguish diverse anomaly patterns through visualizations.
  arXiv  Detail & Related papers  (2024-07-21T19:10:40Z)
• Causal Estimation of Memorisation Profiles [58.20086589761273]
  Understanding memorisation in language models has practical and societal implications. Memorisation is the causal effect of training with an instance on the model's ability to predict that instance. This paper proposes a new, principled, and efficient method to estimate memorisation based on the difference-in-differences design from econometrics.
  arXiv  Detail & Related papers  (2024-06-06T17:59:09Z)
• 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)
• A performance characteristic curve for model evaluation: the application in information diffusion prediction [3.8711489380602804]
  We propose a metric based on information entropy to quantify the randomness in diffusion data, then identify a scaling pattern between the randomness and the prediction accuracy of the model. Data points in the patterns by different sequence lengths, system sizes, and randomness all collapse into a single curve, capturing a model's inherent capability of making correct predictions. The validity of the curve is tested by three prediction models in the same family, reaching conclusions in line with existing studies.
  arXiv  Detail & Related papers  (2023-09-18T07:32:57Z)
• ChiroDiff: Modelling chirographic data with Diffusion Models [132.5223191478268]
  We introduce a powerful model-class namely "Denoising Diffusion Probabilistic Models" or DDPMs for chirographic data. Our model named "ChiroDiff", being non-autoregressive, learns to capture holistic concepts and therefore remains resilient to higher temporal sampling rate.
  arXiv  Detail & Related papers  (2023-04-07T15:17:48Z)
• Neural Superstatistics for Bayesian Estimation of Dynamic Cognitive Models [2.7391842773173334]
  We develop a simulation-based deep learning method for Bayesian inference, which can recover both time-varying and time-invariant parameters. Our results show that the deep learning approach is very efficient in capturing the temporal dynamics of the model.
  arXiv  Detail & Related papers  (2022-11-23T17:42:53Z)
• Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extraction [87.04153383938969]
  We improve the faithfulness of TempRel extraction models from two perspectives. The first perspective is to extract genuinely based on contextual description. The second perspective is to provide proper uncertainty estimation.
  arXiv  Detail & Related papers  (2022-10-10T19:53:13Z)
• Sharing pattern submodels for prediction with missing values [12.981974894538668]
  Missing values are unavoidable in many applications of machine learning and present challenges both during training and at test time. We propose an alternative approach, called sharing pattern submodels, which i) makes predictions robust to missing values at test time, ii) maintains or improves the predictive power of pattern submodels andiii) has a short description, enabling improved interpretability.
  arXiv  Detail & Related papers  (2022-06-22T15:09:40Z)
• Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning [57.4036085386653]
  We show that prompt-based models for sentence pair classification tasks still suffer from a common pitfall of adopting inferences based on lexical overlap. We then show that adding a regularization that preserves pretraining weights is effective in mitigating this destructive tendency of few-shot finetuning.
  arXiv  Detail & Related papers  (2021-09-09T10:10:29Z)
• Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations [64.85696493596821]
  In computer vision applications, generative counterfactual methods indicate how to perturb a model's input to change its prediction. We propose a counterfactual method that learns a perturbation in a disentangled latent space that is constrained using a diversity-enforcing loss. Our model improves the success rate of producing high-quality valuable explanations when compared to previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-03-18T12:57:34Z)
• Modeling Score Distributions and Continuous Covariates: A Bayesian Approach [8.772459063453285]
  We develop a generative model of the match and non-match score distributions over continuous covariates. We use mixture models to capture arbitrary distributions and local basis functions. Three experiments demonstrate the accuracy and effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-09-21T02:41:20Z)

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.