Why Did This Model Forecast This Future? Closed-Form Temporal Saliency Towards Causal Explanations of Probabilistic Forecasts

• URL: http://arxiv.org/abs/2206.00679v1
• Date: Wed, 1 Jun 2022 18:00:04 GMT
• Title: Why Did This Model Forecast This Future? Closed-Form Temporal Saliency Towards Causal Explanations of Probabilistic Forecasts
• Authors: Chirag Raman, Hayley Hung, Marco Loog
• Abstract summary: We build upon a general definition of information-theoretic saliency grounded in human perception. We propose to express the saliency of an observed window in terms of the differential entropy of the resulting predicted future distribution. We empirically demonstrate how our framework can recover salient observed windows from head pose features for the sample task of speaking-turn forecasting.
• Score: 20.442850522575213
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Forecasting tasks surrounding the dynamics of low-level human behavior are of significance to multiple research domains. In such settings, methods for explaining specific forecasts can enable domain experts to gain insights into the predictive relationships between behaviors. In this work, we introduce and address the following question: given a probabilistic forecasting model how can we identify observed windows that the model considers salient when making its forecasts? We build upon a general definition of information-theoretic saliency grounded in human perception and extend it to forecasting settings by leveraging a crucial attribute of the domain: a single observation can result in multiple valid futures. We propose to express the saliency of an observed window in terms of the differential entropy of the resulting predicted future distribution. In contrast to existing methods that either require explicit training of the saliency mechanism or access to the internal states of the forecasting model, we obtain a closed-form solution for the saliency map for commonly used density functions in probabilistic forecasting. We empirically demonstrate how our framework can recover salient observed windows from head pose features for the sample task of speaking-turn forecasting using a synthesized conversation dataset.

Related papers

• When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting [69.30930115236228]
  Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting. Most methods focus on point predictions and do not provide well-calibrated probabilistic forecasts distributions. We propose PROFHiT, a fully probabilistic hierarchical forecasting model that jointly models forecast distribution of entire hierarchy.
  arXiv  Detail & Related papers  (2023-10-17T20:30:16Z)
• PreDiff: Precipitation Nowcasting with Latent Diffusion Models [28.52267957954304]
  We develop a conditional latent diffusion model capable of probabilistic forecasts. We incorporate an explicit knowledge alignment mechanism to align forecasts with domain-specific physical constraints.
  arXiv  Detail & Related papers  (2023-07-19T19:19:13Z)
• TsSHAP: Robust model agnostic feature-based explainability for time series forecasting [6.004928390125367]
  We propose a feature-based explainability algorithm, TsSHAP, that can explain the forecast of any black-box forecasting model. We formalize the notion of local, semi-local, and global explanations in the context of time series forecasting.
  arXiv  Detail & Related papers  (2023-03-22T05:14:36Z)
• TempSAL -- Uncovering Temporal Information for Deep Saliency Prediction [56.22339016797785]
  We introduce a novel saliency prediction model that learns to output saliency maps in sequential time intervals. Our approach locally modulates the saliency predictions by combining the learned temporal maps. Our code will be publicly available on GitHub.
  arXiv  Detail & Related papers  (2023-01-05T22:10:16Z)
• Predicting from Predictions [18.393971232725015]
  We study how causal effects of predictions on outcomes can be identified from observational data. We show that supervised learning that predict from predictions can find transferable functional relationships between features, predictions, and outcomes.
  arXiv  Detail & Related papers  (2022-08-15T16:57:02Z)
• What Should I Know? Using Meta-gradient Descent for Predictive Feature Discovery in a Single Stream of Experience [63.75363908696257]
  computational reinforcement learning seeks to construct an agent's perception of the world through predictions of future sensations. An open challenge in this line of work is determining from the infinitely many predictions that the agent could possibly make which predictions might best support decision-making. We introduce a meta-gradient descent process by which an agent learns what predictions to make, 2) the estimates for its chosen predictions, and 3) how to use those estimates to generate policies that maximize future reward.
  arXiv  Detail & Related papers  (2022-06-13T21:31:06Z)
• Transforming Autoregression: Interpretable and Expressive Time Series Forecast [0.0]
  We propose Autoregressive Transformation Models (ATMs), a model class inspired from various research directions. ATMs unite expressive distributional forecasts using a semi-parametric distribution assumption with an interpretable model specification. We demonstrate the properties of ATMs both theoretically and through empirical evaluation on several simulated and real-world forecasting datasets.
  arXiv  Detail & Related papers  (2021-10-15T17:58:49Z)
• An Interpretable Probabilistic Model for Short-Term Solar Power Forecasting Using Natural Gradient Boosting [0.0]
  We propose a two stage probabilistic forecasting framework able to generate highly accurate, reliable, and sharp forecasts. The framework offers full transparency on both the point forecasts and the prediction intervals (PIs) To highlight the performance and the applicability of the proposed framework, real data from two PV parks located in Southern Germany are employed.
  arXiv  Detail & Related papers  (2021-08-05T12:59:38Z)
• Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecasting [98.57851612518758]
  Probabilistic time series forecasting involves estimating the distribution of future based on its history. We propose a deep state space model for probabilistic time series forecasting whereby the non-linear emission model and transition model are parameterized by networks. We show in experiments that our model produces accurate and sharp probabilistic forecasts.
  arXiv  Detail & Related papers  (2021-01-31T06:49:33Z)
• Forethought and Hindsight in Credit Assignment [62.05690959741223]
  We work to understand the gains and peculiarities of planning employed as forethought via forward models or as hindsight operating with backward models. We investigate the best use of models in planning, primarily focusing on the selection of states in which predictions should be (re)-evaluated.
  arXiv  Detail & Related papers  (2020-10-26T16:00:47Z)
• Video Prediction via Example Guidance [156.08546987158616]
  In video prediction tasks, one major challenge is to capture the multi-modal nature of future contents and dynamics. In this work, we propose a simple yet effective framework that can efficiently predict plausible future states.
  arXiv  Detail & Related papers  (2020-07-03T14:57:24Z)

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.