- Award ID(s):
- 1927554
- NSF-PAR ID:
- 10391935
- Date Published:
- Journal Name:
- On the Sensitivity and Stability of Model Interpretations in NLP
- Page Range / eLocation ID:
- 2631 to 2647
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
Ye, Yuting ; Wang Huamin (Ed.)We analyze a wide class of penalty energies used for contact response through the lens of a reduced frame. Applying our analysis to both spring-based and barrier-based energies, we show that we can obtain closed-form, analytic eigensystems that can be used to guarantee positive semidefiniteness in implicit solvers. Our approach is both faster than direct numerical methods, and more robust than approximate methods such as Gauss-Newton. Over the course of our analysis, we investigate physical interpretations for two separate notions of length. Finally, we showcase the stability of our analysis on challenging strand, cloth, and volume scenarios with large timesteps on the order of 1/40 s.more » « less
-
ABSTRACT Morphology forms the most fundamental level of data in vertebrate palaeontology because it is through interpretations of morphology that taxa are identified, creating the basis for broad evolutionary and palaeobiological hypotheses. Assessing maturity is one of the most basic aspects of morphological interpretation and provides the means to study the evolution of ontogenetic changes, population structure and palaeoecology, life‐history strategies, and heterochrony along evolutionary lineages that would otherwise be lost to time. Saurian reptiles (the least‐inclusive clade containing Lepidosauria and Archosauria) have remained an incredibly diverse, numerous, and disparate clade through their ~260‐million‐year history. Because of the great disparity in this group, assessing maturity of saurian reptiles is difficult, fraught with methodological and terminological ambiguity. We compiled a novel database of literature, assembling >900 individual instances of saurian maturity assessment, to examine critically how saurian maturity has been diagnosed. We review the often inexact and inconsistent terminology used in saurian maturity assessment (e.g. ‘juvenile’, ‘mature’) and provide routes for better clarity and cross‐study coherence. We describe the various methods that have been used to assess maturity in every major saurian group, integrating data from both extant and extinct taxa to give a full account of the current state of the field and providing method‐specific pitfalls, best practices, and fruitful directions for future research. We recommend that a new standard subsection, ‘Ontogenetic Assessment’, be added to the Systematic Palaeontology portions of descriptive studies to provide explicit ontogenetic diagnoses with clear criteria. Because the utility of different ontogenetic criteria is highly subclade dependent among saurians, even for widely used methods (e.g. neurocentral suture fusion), we recommend that phylogenetic context, preferably in the form of a phylogenetic bracket, be used to justify the use of a maturity assessment method. Different methods should be used in conjunction as independent lines of evidence when assessing maturity, instead of an ontogenetic diagnosis resting entirely on a single criterion, which is common in the literature. Critically, there is a need for data from extant taxa with well‐represented growth series to be integrated with the fossil record to ground maturity assessments of extinct taxa in well‐constrained, empirically tested methods.
-
Given the widespread deployment of black box deep neural networks in computer vision applications, the interpretability aspect of these black box systems has recently gained traction. Various methods have been proposed to explain the results of such deep neural networks. However, some recent works have shown that such explanation methods are biased and do not produce consistent interpretations. Hence, rather than introducing a novel explanation method, we learn models that are encouraged to be interpretable given an explanation method. We use Grad-CAM as the explanation algorithm and encourage the network to learn consistent interpretations along with maximizing the log-likelihood of the correct class. We show that our method outperforms the baseline on the pointing game evaluation on ImageNet and MS-COCO datasets respectively. We also introduce new evaluation metrics that penalize the saliency map if it lies outside the ground truth bounding box or segmentation mask, and show that our method outperforms the baseline on these metrics as well. Moreover, our model trained with interpretation consistency generalizes to other explanation algorithms on all the evaluation metrics.more » « less
-
null (Ed.)Recent work in fair machine learning has proposed dozens of technical definitions of algorithmic fairness and methods for enforcing these definitions. However, we still lack an understanding of how to develop machine learning systems with fairness criteria that reflect relevant stakeholders’ nuanced viewpoints in real-world contexts. To address this gap, we propose a framework for eliciting stakeholders’ subjective fairness notions. Combining a user interface that allows stakeholders to examine the data and the algorithm’s predictions with an interview protocol to probe stakeholders’ thoughts while they are interacting with the interface, we can identify stakeholders’ fairness beliefs and principles. We conduct a user study to evaluate our framework in the setting of a child maltreatment predictive system. Our evaluations show that the framework allows stakeholders to comprehensively convey their fairness viewpoints. We also discuss how our results can inform the design of predictive systems.more » « less
-
Machine-learning models have demonstrated great success in learning complex patterns that enable them to make predictions about unobserved data. In addition to using models for prediction, the ability to interpret what a model has learned is receiving an increasing amount of attention. However, this increased focus has led to considerable confusion about the notion of interpretability. In particular, it is unclear how the wide array of proposed interpretation methods are related and what common concepts can be used to evaluate them. We aim to address these concerns by defining interpretability in the context of machine learning and introducing the predictive, descriptive, relevant (PDR) framework for discussing interpretations. The PDR framework provides 3 overarching desiderata for evaluation: predictive accuracy, descriptive accuracy, and relevancy, with relevancy judged relative to a human audience. Moreover, to help manage the deluge of interpretation methods, we introduce a categorization of existing techniques into model-based and post hoc categories, with subgroups including sparsity, modularity, and simulatability. To demonstrate how practitioners can use the PDR framework to evaluate and understand interpretations, we provide numerous real-world examples. These examples highlight the often underappreciated role played by human audiences in discussions of interpretability. Finally, based on our framework, we discuss limitations of existing methods and directions for future work. We hope that this work will provide a common vocabulary that will make it easier for both practitioners and researchers to discuss and choose from the full range of interpretation methods.more » « less