Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?
- URL: http://arxiv.org/abs/2402.06160v2
- Date: Wed, 12 Jun 2024 18:37:40 GMT
- Title: Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?
- Authors: Maohao Shen, J. Jon Ryu, Soumya Ghosh, Yuheng Bu, Prasanna Sattigeri, Subhro Das, Gregory W. Wornell,
- Abstract summary: EDL methods are trained to learn a meta distribution over the predictive distribution by minimizing a specific objective function.
Recent studies identify limitations of the existing methods to conclude their learned uncertainties are unreliable.
We provide a sharper understanding of the behavior of a wide class of EDL methods by unifying various objective functions.
We conclude that even when EDL methods are empirically effective on downstream tasks, this occurs despite their poor uncertainty quantification capabilities.
- Score: 35.15844215216846
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: This paper questions the effectiveness of a modern predictive uncertainty quantification approach, called \emph{evidential deep learning} (EDL), in which a single neural network model is trained to learn a meta distribution over the predictive distribution by minimizing a specific objective function. Despite their perceived strong empirical performance on downstream tasks, a line of recent studies by Bengs et al. identify limitations of the existing methods to conclude their learned epistemic uncertainties are unreliable, e.g., in that they are non-vanishing even with infinite data. Building on and sharpening such analysis, we 1) provide a sharper understanding of the asymptotic behavior of a wide class of EDL methods by unifying various objective functions; 2) reveal that the EDL methods can be better interpreted as an out-of-distribution detection algorithm based on energy-based-models; and 3) conduct extensive ablation studies to better assess their empirical effectiveness with real-world datasets. Through all these analyses, we conclude that even when EDL methods are empirically effective on downstream tasks, this occurs despite their poor uncertainty quantification capabilities. Our investigation suggests that incorporating model uncertainty can help EDL methods faithfully quantify uncertainties and further improve performance on representative downstream tasks, albeit at the cost of additional computational complexity.
Related papers
- Learning Latent Graph Structures and their Uncertainty [63.95971478893842]
Graph Neural Networks (GNNs) use relational information as an inductive bias to enhance the model's accuracy.
As task-relevant relations might be unknown, graph structure learning approaches have been proposed to learn them while solving the downstream prediction task.
arXiv Detail & Related papers (2024-05-30T10:49:22Z) - Uncertainty for Active Learning on Graphs [70.44714133412592]
Uncertainty Sampling is an Active Learning strategy that aims to improve the data efficiency of machine learning models.
We benchmark Uncertainty Sampling beyond predictive uncertainty and highlight a significant performance gap to other Active Learning strategies.
We develop ground-truth Bayesian uncertainty estimates in terms of the data generating process and prove their effectiveness in guiding Uncertainty Sampling toward optimal queries.
arXiv Detail & Related papers (2024-05-02T16:50:47Z) - STAR: Constraint LoRA with Dynamic Active Learning for Data-Efficient Fine-Tuning of Large Language Models [21.929902181609936]
We propose a novel approach to integrate uncertainty-based active learning and LoRA.
For the uncertainty gap, we introduce a dynamic uncertainty measurement that combines the uncertainty of the base model and the uncertainty of the full model.
For poor model calibration, we incorporate the regularization method during LoRA training to keep the model from being over-confident.
arXiv Detail & Related papers (2024-03-02T10:38:10Z) - Uncertainty Quantification for In-Context Learning of Large Language Models [52.891205009620364]
In-context learning has emerged as a groundbreaking ability of Large Language Models (LLMs)
We propose a novel formulation and corresponding estimation method to quantify both types of uncertainties.
The proposed method offers an unsupervised way to understand the prediction of in-context learning in a plug-and-play fashion.
arXiv Detail & Related papers (2024-02-15T18:46:24Z) - Beyond Fidelity: Explaining Vulnerability Localization of Learning-based
Detectors [10.316819421902363]
Vulnerability detectors based on deep learning (DL) models have proven their effectiveness in recent years.
The shroud of opacity surrounding the decision-making process of these detectors makes it difficult for security analysts to comprehend.
We evaluate the performance of ten explanation approaches for vulnerability detectors based on graph and sequence representations.
arXiv Detail & Related papers (2024-01-05T07:37:35Z) - Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling [69.83976050879318]
In large language models (LLMs), identifying sources of uncertainty is an important step toward improving reliability, trustworthiness, and interpretability.
In this paper, we introduce an uncertainty decomposition framework for LLMs, called input clarification ensembling.
Our approach generates a set of clarifications for the input, feeds them into an LLM, and ensembles the corresponding predictions.
arXiv Detail & Related papers (2023-11-15T05:58:35Z) - Offline Reinforcement Learning with Additional Covering Distributions [0.0]
We study learning optimal policies from a logged dataset, i.e., offline RL, with function approximation.
We show that sample-efficient offline RL for general MDPs is possible with only a partial coverage dataset and weak realizable function classes.
arXiv Detail & Related papers (2023-05-22T03:31:03Z) - Uncertainty Estimation by Fisher Information-based Evidential Deep
Learning [61.94125052118442]
Uncertainty estimation is a key factor that makes deep learning reliable in practical applications.
We propose a novel method, Fisher Information-based Evidential Deep Learning ($mathcalI$-EDL)
In particular, we introduce Fisher Information Matrix (FIM) to measure the informativeness of evidence carried by each sample, according to which we can dynamically reweight the objective loss terms to make the network more focused on the representation learning of uncertain classes.
arXiv Detail & Related papers (2023-03-03T16:12:59Z) - Accurate and Robust Feature Importance Estimation under Distribution
Shifts [49.58991359544005]
PRoFILE is a novel feature importance estimation method.
We show significant improvements over state-of-the-art approaches, both in terms of fidelity and robustness.
arXiv Detail & Related papers (2020-09-30T05:29:01Z)
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.