How does this interaction affect me? Interpretable attribution for feature interactions

• URL: http://arxiv.org/abs/2006.10965v1
• Date: Fri, 19 Jun 2020 05:14:24 GMT
• Title: How does this interaction affect me? Interpretable attribution for feature interactions
• Authors: Michael Tsang, Sirisha Rambhatla, Yan Liu
• Abstract summary: We propose an interaction attribution and detection framework called Archipelago. Our experiments on standard annotation labels indicate our approach provides significantly more interpretable explanations than comparable methods. We also provide accompanying visualizations of our approach that give new insights into deep neural networks.
• Score: 19.979889568380464
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine learning transparency calls for interpretable explanations of how inputs relate to predictions. Feature attribution is a way to analyze the impact of features on predictions. Feature interactions are the contextual dependence between features that jointly impact predictions. There are a number of methods that extract feature interactions in prediction models; however, the methods that assign attributions to interactions are either uninterpretable, model-specific, or non-axiomatic. We propose an interaction attribution and detection framework called Archipelago which addresses these problems and is also scalable in real-world settings. Our experiments on standard annotation labels indicate our approach provides significantly more interpretable explanations than comparable methods, which is important for analyzing the impact of interactions on predictions. We also provide accompanying visualizations of our approach that give new insights into deep neural networks.

Related papers

• SSL-Interactions: Pretext Tasks for Interactive Trajectory Prediction [4.286256266868156]
  We present SSL-Interactions that proposes pretext tasks to enhance interaction modeling for trajectory prediction. We introduce four interaction-aware pretext tasks to encapsulate various aspects of agent interactions. We also propose an approach to curate interaction-heavy scenarios from datasets.
  arXiv  Detail & Related papers  (2024-01-15T14:43:40Z)
• Disentangled Interaction Representation for One-Stage Human-Object Interaction Detection [70.96299509159981]
  Human-Object Interaction (HOI) detection is a core task for human-centric image understanding. Recent one-stage methods adopt a transformer decoder to collect image-wide cues that are useful for interaction prediction. Traditional two-stage methods benefit significantly from their ability to compose interaction features in a disentangled and explainable manner.
  arXiv  Detail & Related papers  (2023-12-04T08:02:59Z)
• 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)
• Exploring the cloud of feature interaction scores in a Rashomon set [17.775145325515993]
  We introduce the feature interaction score (FIS) in the context of a Rashomon set. We demonstrate the properties of the FIS via synthetic data and draw connections to other areas of statistics. Our results suggest that the proposed FIS can provide valuable insights into the nature of feature interactions in machine learning models.
  arXiv  Detail & Related papers  (2023-05-17T13:05:26Z)
• Asymmetric feature interaction for interpreting model predictions [13.934784414106087]
  In natural language processing, deep neural networks (DNNs) could model complex interactions between context. We propose an asymmetric feature interaction attribution model that aims to explore asymmetric higher-order feature interactions. Experimental results on two sentiment classification datasets show the superiority of our model against the state-of-the-art feature interaction attribution methods.
  arXiv  Detail & Related papers  (2023-05-12T03:31:24Z)
• REPID: Regional Effect Plots with implicit Interaction Detection [0.9023847175654603]
  Interpretable machine learning methods visualize marginal feature effects but may lead to misleading interpretations when feature interactions are present. We introduce implicit interaction detection, a novel framework to detect interactions between a feature of interest and other features. The framework also quantifies the strength of interactions and provides interpretable and distinct regions in which feature effects can be interpreted more reliably.
  arXiv  Detail & Related papers  (2022-02-15T08:54:00Z)
• You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction [52.442129609979794]
  Recent deep learning approaches for trajectory prediction show promising performance. It remains unclear which features such black-box models actually learn to use for making predictions. This paper proposes a procedure that quantifies the contributions of different cues to model performance.
  arXiv  Detail & Related papers  (2021-10-11T14:24:15Z)
• Information Interaction Profile of Choice Adoption [2.9972063833424216]
  We introduce an efficient method to infer the entities interaction network and its evolution according to the temporal distance separating interacting entities. The interaction profile allows characterizing the mechanisms of the interaction processes. We show that the effect of a combination of exposures on a user is more than the sum of each exposure's independent effect--there is an interaction.
  arXiv  Detail & Related papers  (2021-04-28T10:42:25Z)
• Causal Discovery in Physical Systems from Videos [123.79211190669821]
  Causal discovery is at the core of human cognition. We consider the task of causal discovery from videos in an end-to-end fashion without supervision on the ground-truth graph structure.
  arXiv  Detail & Related papers  (2020-07-01T17:29:57Z)
• Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions [55.660255727031725]
  Influence functions explain the decisions of a model by identifying influential training examples. We conduct a comparison between influence functions and common word-saliency methods on representative tasks. We develop a new measure based on influence functions that can reveal artifacts in training data.
  arXiv  Detail & Related papers  (2020-05-14T00:45:23Z)
• Self-Attention Attribution: Interpreting Information Interactions Inside Transformer [89.21584915290319]
  We propose a self-attention attribution method to interpret the information interactions inside Transformer. We show that the attribution results can be used as adversarial patterns to implement non-targeted attacks towards BERT.
  arXiv  Detail & Related papers  (2020-04-23T14:58:22Z)

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.