paper-with-me

Papers

Improving evidential deep learning via multi-task learning

2021-12-17 · Dongpin Oh, Bonggun Shin

The Evidential regression network (ENet) estimates a continuous target and its predictive uncertainty without costly Bayesian model averaging. However, it is possible that the target is inaccurately predicted due to the gradient shrinkage problem of the original loss function of the ENet, the negative log marginal likelihood (NLL) loss. In this paper, the objective is to improve the prediction accuracy of the ENet while maintaining its efficient uncertainty estimation by resolving the gradient shrinkage problem. A multi-task learning (MTL) framework, referred to as MT-ENet, is proposed to accomplish this aim. In the MTL, we define the Lipschitz modified mean squared error (MSE) loss function as another loss and add it to the existing NLL loss. The Lipschitz modified MSE loss is designed to mitigate the gradient conflict with the NLL loss by dynamically adjusting its Lipschitz constant. By doing so, the Lipschitz MSE loss does not disturb the uncertainty estimation of the NLL loss. The MT-ENet enhances the predictive accuracy of the ENet without losing uncertainty estimation capability on the synthetic dataset and real-world benchmarks, including drug-target affinity (DTA) regression. Furthermore, the MT-ENet shows remarkable calibration and out-of-distribution detection capability on the DTA benchmarks.

📄 PDF Abstract BibTeX arXiv:2112.09368

Code (1)

deargen/MT-ENet pytorch

Tasks

Deep LearningMulti-Task LearningOut-of-Distribution Detectionregression

Methods 이 논문이 사용한 방법론

Dilated Convolution 설명 없음
ENet Initial Block The ENet Initial Block is an image model block used in the ENet semantic segmentation architecture. [Max…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
ENet Dilated Bottleneck ENet Dilated Bottleneck is an image model block used in the ENet semantic segmentation architecture. It is the same as a regular…
SpatialDropout SpatialDropout is a type of dropout for convolutional networks. For a given…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Similar Papers 제목 키워드 기반

Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Retrieval-augmented generation models have shown state-of-the-art performance across many knowledge-intensive NLP tasks such as open question answering and fact verification. These models are trained to generate a final …

Fact VerificationMemorizationMulti-Task LearningOpen-Domain Question Answering+4

Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks

2021-12-16 · NAACL 2022 7 · Akari Asai, Matt Gardner, Hannaneh Hajishirzi

Retrieval-augmented generation models have shown state-of-the-art performance across many knowledge-intensive NLP tasks such as open question answering and fact verification. These models are trained to generate the fina…

AttributeFact VerificationMemorizationMulti-Task Learning+4

EvidMTL: Evidential Multi-Task Learning for Uncertainty-Aware Semantic Surface Mapping from Monocular RGB Images

2025-03-06 · Rohit Menon, Nils Dengler, Sicong Pan, Gokul Krishna Chenchani 외

For scene understanding in unstructured environments, an accurate and uncertainty-aware metric-semantic mapping is required to enable informed action selection by autonomous systems. Existing mapping methods often suffer…

Depth EstimationDepth PredictionMulti-Task LearningScene Understanding+2

Multivariate Deep Evidential Regression

2021-04-13 · Nis Meinert, Alexander Lavin

There is significant need for principled uncertainty reasoning in machine learning systems as they are increasingly deployed in safety-critical domains. A new approach with uncertainty-aware neural networks (NNs), based …

regression

Medical Image Segmentation with Belief Function Theory and Deep Learning

2023-09-12 · Ling Huang

Deep learning has shown promising contributions in medical image segmentation with powerful learning and feature representation abilities. However, it has limitations for reasoning with and combining imperfect (imprecise…

Deep LearningImage SegmentationMedical Image SegmentationSegmentation+3