A Typology for Exploring the Mitigation of Shortcut Behavior

• URL: http://arxiv.org/abs/2203.03668v6
• Date: Thu, 14 Mar 2024 15:25:16 GMT
• Title: A Typology for Exploring the Mitigation of Shortcut Behavior
• Authors: Felix Friedrich, Wolfgang Stammer, Patrick Schramowski, Kristian Kersting,
• Abstract summary: We provide a unification of various XIL methods into a single typology by establishing a common set of basic modules. In our evaluations, all methods prove to revise a model successfully. However, we found remarkable differences in individual benchmark tasks, revealing valuable application-relevant aspects.
• Score: 29.38025128165229
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As machine learning models become increasingly larger, trained weakly supervised on large, possibly uncurated data sets, it becomes increasingly important to establish mechanisms for inspecting, interacting, and revising models to mitigate learning shortcuts and guarantee their learned knowledge is aligned with human knowledge. The recently proposed XIL framework was developed for this purpose, and several such methods have been introduced, each with individual motivations and methodological details. In this work, we provide a unification of various XIL methods into a single typology by establishing a common set of basic modules. In doing so, we pave the way for a principled comparison of existing, but, importantly, also future XIL approaches. In addition, we discuss existing and introduce novel measures and benchmarks for evaluating the overall abilities of a XIL method. Given this extensive toolbox, including our typology, measures, and benchmarks, we finally compare several recent XIL methods methodologically and quantitatively. In our evaluations, all methods prove to revise a model successfully. However, we found remarkable differences in individual benchmark tasks, revealing valuable application-relevant aspects for integrating these benchmarks in developing future methods.

Related papers

• Enhancing binary classification: A new stacking method via leveraging computational geometry [5.906199156511947]
  This paper introduces a novel approach that integrates computational geometry techniques, specifically solving the maximum weighted rectangle problem, to develop a new meta-model for binary classification. Our method is evaluated on multiple open datasets, with statistical analysis showing its stability and demonstrating improvements in accuracy. Our method is highly applicable not only in stacking ensemble learning but also in various real-world applications, such as hospital health evaluation scoring and bank credit scoring systems.
  arXiv  Detail & Related papers  (2024-10-30T06:11:08Z)
• Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities [89.40778301238642]
  Model merging is an efficient empowerment technique in the machine learning community. There is a significant gap in the literature regarding a systematic and thorough review of these techniques.
  arXiv  Detail & Related papers  (2024-08-14T16:58:48Z)
• A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning [136.89318317245855]
  MoErging aims to recycle expert models to create an aggregate system with improved performance or generalization. A key component of MoErging methods is the creation of a router that decides which expert model(s) to use for a particular input or application. This survey includes a novel taxonomy for cataloging key design choices and clarifying suitable applications for each method.
  arXiv  Detail & Related papers  (2024-08-13T17:49:00Z)
• POGEMA: A Benchmark Platform for Cooperative Multi-Agent Navigation [76.67608003501479]
  We introduce and specify an evaluation protocol defining a range of domain-related metrics computed on the basics of the primary evaluation indicators. The results of such a comparison, which involves a variety of state-of-the-art MARL, search-based, and hybrid methods, are presented.
  arXiv  Detail & Related papers  (2024-07-20T16:37:21Z)
• EXACT: Towards a platform for empirically benchmarking Machine Learning model explanation methods [1.6383837447674294]
  This paper brings together various benchmark datasets and novel performance metrics in an initial benchmarking platform. Our datasets incorporate ground truth explanations for class-conditional features. This platform assesses the performance of post-hoc XAI methods in the quality of the explanations they produce.
  arXiv  Detail & Related papers  (2024-05-20T14:16:06Z)
• Experimental Analysis of Large-scale Learnable Vector Storage Compression [42.52474894105165]
  Learnable embedding vector is one of the most important applications in machine learning. The high dimensionality of sparse data in recommendation tasks and the huge volume of corpus in retrieval-related tasks lead to a large memory consumption of the embedding table. Recent research has proposed various methods to compress the embeddings at the cost of a slight decrease in model quality or the introduction of other overheads.
  arXiv  Detail & Related papers  (2023-11-27T07:11:47Z)
• Generalization Properties of Retrieval-based Models [50.35325326050263]
  Retrieval-based machine learning methods have enjoyed success on a wide range of problems. Despite growing literature showcasing the promise of these models, the theoretical underpinning for such models remains underexplored. We present a formal treatment of retrieval-based models to characterize their generalization ability.
  arXiv  Detail & Related papers  (2022-10-06T00:33:01Z)
• On the role of benchmarking data sets and simulations in method comparison studies [0.0]
  This paper investigates differences and similarities between simulation studies and benchmarking studies. We borrow ideas from different contexts such as mixed methods research and Clinical Scenario Evaluation.
  arXiv  Detail & Related papers  (2022-08-02T13:47:53Z)
• EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients [2.0935101589828244]
  Few-shot learning aims at leveraging knowledge learned by one or more deep learning models, in order to obtain good classification performance on new problems. We propose a simple methodology, that reaches or even beats state of the art performance on multiple standardized benchmarks of the field.
  arXiv  Detail & Related papers  (2022-01-24T14:08:23Z)
• A Survey on Deep Semi-supervised Learning [51.26862262550445]
  We first present a taxonomy for deep semi-supervised learning that categorizes existing methods. We then offer a detailed comparison of these methods in terms of the type of losses, contributions, and architecture differences.
  arXiv  Detail & Related papers  (2021-02-28T16:22:58Z)
• Evaluating the Disentanglement of Deep Generative Models through Manifold Topology [66.06153115971732]
  We present a method for quantifying disentanglement that only uses the generative model. We empirically evaluate several state-of-the-art models across multiple datasets.
  arXiv  Detail & Related papers  (2020-06-05T20:54:11Z)

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.