Gradient-based Explanations for Deep Learning Survival Models

• URL: http://arxiv.org/abs/2502.04970v1
• Date: Fri, 07 Feb 2025 14:36:55 GMT
• Title: Gradient-based Explanations for Deep Learning Survival Models
• Authors: Sophie Hanna Langbein, Niklas Koenen, Marvin N. Wright,
• Abstract summary: We propose a framework for gradient-based explanation methods tailored to survival neural networks. We analyze the implications of their theoretical assumptions for time-dependent explanations in the survival setting. We propose effective visualizations incorporating the temporal dimension.
• Score: 0.716879432974126
• License:
• Abstract: Deep learning survival models often outperform classical methods in time-to-event predictions, particularly in personalized medicine, but their "black box" nature hinders broader adoption. We propose a framework for gradient-based explanation methods tailored to survival neural networks, extending their use beyond regression and classification. We analyze the implications of their theoretical assumptions for time-dependent explanations in the survival setting and propose effective visualizations incorporating the temporal dimension. Experiments on synthetic data show that gradient-based methods capture the magnitude and direction of local and global feature effects, including time dependencies. We introduce GradSHAP(t), a gradient-based counterpart to SurvSHAP(t), which outperforms SurvSHAP(t) and SurvLIME in a computational speed vs. accuracy trade-off. Finally, we apply these methods to medical data with multi-modal inputs, revealing relevant tabular features and visual patterns, as well as their temporal dynamics.

Related papers

• Time-series attribution maps with regularized contrastive learning [1.5503410315996757]
  gradient-based attribution methods aim to explain decisions of deep learning models but so far lack identifiability guarantees. Here, we propose a method to generate attribution maps with identifiability guarantees by developing a regularized contrastive learning algorithm trained on time-series data. We show theoretically that xCEBRA has favorable properties for identifying the Jacobian matrix of the data generating process.
  arXiv  Detail & Related papers  (2025-02-17T18:34:25Z)
• Conservation-informed Graph Learning for Spatiotemporal Dynamics Prediction [84.26340606752763]
  In this paper, we introduce the conservation-informed GNN (CiGNN), an end-to-end explainable learning framework. The network is designed to conform to the general symmetry conservation law via symmetry where conservative and non-conservative information passes over a multiscale space by a latent temporal marching strategy. Results demonstrate that CiGNN exhibits remarkable baseline accuracy and generalizability, and is readily applicable to learning for prediction of varioustemporal dynamics.
  arXiv  Detail & Related papers  (2024-12-30T13:55:59Z)
• Deep End-to-End Survival Analysis with Temporal Consistency [49.77103348208835]
  We present a novel Survival Analysis algorithm designed to efficiently handle large-scale longitudinal data. A central idea in our method is temporal consistency, a hypothesis that past and future outcomes in the data evolve smoothly over time. Our framework uniquely incorporates temporal consistency into large datasets by providing a stable training signal.
  arXiv  Detail & Related papers  (2024-10-09T11:37:09Z)
• Physics-guided Active Sample Reweighting for Urban Flow Prediction [75.24539704456791]
  Urban flow prediction is a nuanced-temporal modeling that estimates the throughput of transportation services like buses, taxis and ride-driven models. Some recent prediction solutions bring remedies with the notion of physics-guided machine learning (PGML) We develop a atized physics-guided network (PN), and propose a data-aware framework Physics-guided Active Sample Reweighting (P-GASR)
  arXiv  Detail & Related papers  (2024-07-18T15:44:23Z)
• Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation [53.27596811146316]
  Diffusion models operate over a sequence of timesteps instead of instantaneous input-output relationships in previous contexts. We present Diffusion-TracIn that incorporates this temporal dynamics and observe that samples' loss gradient norms are highly dependent on timestep. We introduce Diffusion-ReTrac as a re-normalized adaptation that enables the retrieval of training samples more targeted to the test sample of interest.
  arXiv  Detail & Related papers  (2024-01-17T07:58:18Z)
• OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning [67.07363529640784]
  We propose OpenSTL to categorize prevalent approaches into recurrent-based and recurrent-free models. We conduct standard evaluations on datasets across various domains, including synthetic moving object trajectory, human motion, driving scenes, traffic flow and forecasting weather. We find that recurrent-free models achieve a good balance between efficiency and performance than recurrent models.
  arXiv  Detail & Related papers  (2023-06-20T03:02:14Z)
• TempSAL -- Uncovering Temporal Information for Deep Saliency Prediction [64.63645677568384]
  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)
• Mixed moving average field guided learning for spatio-temporal data [0.0]
  We define a novel Bayesian-temporal embedding and a theory-guided machine learning approach to make ensemble forecasts. We use Lipschitz predictors to determine fixed-time and any-time PAC in the batch learning setting. We then test the performance of our learning methodology by using linear predictors and data sets simulated from a dependence- Ornstein-Uhlenbeck process.
  arXiv  Detail & Related papers  (2023-01-02T16:11:05Z)
• DeepHazard: neural network for time-varying risks [0.6091702876917281]
  We propose a new flexible method for survival prediction: DeepHazard, a neural network for time-varying risks. Our approach is tailored for a wide range of continuous hazards forms, with the only restriction of being additive in time. Numerical examples illustrate that our approach outperforms existing state-of-the-art methodology in terms of predictive capability evaluated through the C-index metric.
  arXiv  Detail & Related papers  (2020-07-26T21:01:49Z)

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.