On the Robustness of Global Feature Effect Explanations

• URL: http://arxiv.org/abs/2406.09069v1
• Date: Thu, 13 Jun 2024 12:54:53 GMT
• Title: On the Robustness of Global Feature Effect Explanations
• Authors: Hubert Baniecki, Giuseppe Casalicchio, Bernd Bischl, Przemyslaw Biecek,
• Abstract summary: Effects of predictor features in black-box supervised learning are an essential diagnostic tool for model and scientific discovery in applied sciences. We introduce several theoretical bounds for evaluating the robustness of partial dependence plots and accumulated local effects.
• Score: 17.299418894910627
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study the robustness of global post-hoc explanations for predictive models trained on tabular data. Effects of predictor features in black-box supervised learning are an essential diagnostic tool for model debugging and scientific discovery in applied sciences. However, how vulnerable they are to data and model perturbations remains an open research question. We introduce several theoretical bounds for evaluating the robustness of partial dependence plots and accumulated local effects. Our experimental results with synthetic and real-world datasets quantify the gap between the best and worst-case scenarios of (mis)interpreting machine learning predictions globally.

Related papers

• DAG-aware Transformer for Causal Effect Estimation [0.8192907805418583]
  Causal inference is a critical task across fields such as healthcare, economics, and the social sciences. In this paper, we present a novel transformer-based method for causal inference that overcomes these challenges. The core innovation of our model lies in its integration of causal Directed Acyclic Graphs (DAGs) directly into the attention mechanism.
  arXiv  Detail & Related papers  (2024-10-13T23:17:58Z)
• EXMOS: Explanatory Model Steering Through Multifaceted Explanations and Data Configurations [5.132827811038276]
  This research investigates the influence of data-centric and model-centric explanations in interactive machine-learning systems. We conducted studies with healthcare experts to explore the impact of different explanations on trust, understandability and model improvement. Our results reveal the insufficiency of global model-centric explanations for guiding users during data configuration.
  arXiv  Detail & Related papers  (2024-02-01T10:57:00Z)
• A PAC-Bayesian Perspective on the Interpolating Information Criterion [54.548058449535155]
  We show how a PAC-Bayes bound is obtained for a general class of models, characterizing factors which influence performance in the interpolating regime. We quantify how the test error for overparameterized models achieving effectively zero training error depends on the quality of the implicit regularization imposed by e.g. the combination of model, parameter-initialization scheme.
  arXiv  Detail & Related papers  (2023-11-13T01:48:08Z)
• On the Joint Interaction of Models, Data, and Features [82.60073661644435]
  We introduce a new tool, the interaction tensor, for empirically analyzing the interaction between data and model through features. Based on these observations, we propose a conceptual framework for feature learning. Under this framework, the expected accuracy for a single hypothesis and agreement for a pair of hypotheses can both be derived in closed-form.
  arXiv  Detail & Related papers  (2023-06-07T21:35:26Z)
• Data-Driven Estimation of Heterogeneous Treatment Effects [15.140272661540655]
  Estimating how a treatment affects different individuals, known as heterogeneous treatment effect estimation, is an important problem in empirical sciences. We provide a survey of state-of-the-art data-driven methods for heterogeneous treatment effect estimation using machine learning.
  arXiv  Detail & Related papers  (2023-01-16T21:36:49Z)
• Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions [59.284907093349425]
  Large amounts of training data are one of the major reasons for the high performance of state-of-the-art NLP models. We provide a language for describing how training data influences predictions, through a causal framework. Our framework bypasses the need to retrain expensive models and allows us to estimate causal effects based on observational data alone.
  arXiv  Detail & Related papers  (2022-07-28T17:36:24Z)
• Building Autocorrelation-Aware Representations for Fine-Scale Spatiotemporal Prediction [1.2862507359003323]
  We present a novel deep learning architecture that incorporates theories of spatial statistics into neural networks. DeepLATTE contains an autocorrelation-guided semi-supervised learning strategy to enforce both local autocorrelation patterns and global autocorrelation trends. We conduct a demonstration of DeepLATTE using publicly available data for an important public health topic, air quality prediction in a well-fitting, complex physical environment.
  arXiv  Detail & Related papers  (2021-12-10T03:21:19Z)
• Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach [80.8446673089281]
  We propose a new learning paradigm with graph representation and learning. Our framework contains two modules: 1) a backbone network (e.g., feedforward neural nets) as a lower model takes features as input and outputs predicted labels; 2) a graph neural network as an upper model learns to extrapolate embeddings for new features via message passing over a feature-data graph built from observed data.
  arXiv  Detail & Related papers  (2021-10-09T09:02:45Z)
• Learning Neural Causal Models with Active Interventions [83.44636110899742]
  We introduce an active intervention-targeting mechanism which enables a quick identification of the underlying causal structure of the data-generating process. Our method significantly reduces the required number of interactions compared with random intervention targeting. We demonstrate superior performance on multiple benchmarks from simulated to real-world data.
  arXiv  Detail & Related papers  (2021-09-06T13:10:37Z)
• Influence Functions in Deep Learning Are Fragile [52.31375893260445]
  influence functions approximate the effect of samples in test-time predictions. influence estimates are fairly accurate for shallow networks. Hessian regularization is important to get highquality influence estimates.
  arXiv  Detail & Related papers  (2020-06-25T18:25:59Z)
• Causal Discovery from Incomplete Data: A Deep Learning Approach [21.289342482087267]
  Imputated Causal Learning is proposed to perform iterative missing data imputation and causal structure discovery. We show that ICL can outperform state-of-the-art methods under different missing data mechanisms.
  arXiv  Detail & Related papers  (2020-01-15T14:28:21Z)

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.