paper-with-me

Papers

Adaptive Pseudo-labeling for Quantum Calculations

2021-09-24 · NeurIPS Workshop AI4Scien 2021 12 · Kexin Huang, Vishnu Sresht, Brajesh Rai, Mykola Bordyuh

Machine learning models have recently shown promise in predicting molecular quantum chemical properties. However, the path to real-life adoption requires (1) learning under low-resource constraint and (2) out-of-distribution generalization to unseen, structurally diverse molecules. We observe that these two challenges originate from label scarcity issue. We hypothesize that pseudo-labeling on vast array of unlabeled molecules can serve as proxies as gold-label to greatly expand the training labeled data. The challenge in pseudo-labeling is to prevent the bad pseudo-labels from biasing the model. We develop a simple and effective strategy Pseudo-Sigma that can assign pseudo-labels, detect bad pseud-labels through evidential uncertainty, and then prevent them from biasing the model using adaptive weighting. Empirically, Pseudo-Sigma improves quantum calculations accuracy across full data, low data and out-of-distribution settings.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Out-of-Distribution Generalization

Similar Papers 제목 키워드 기반

Semi-supervision semantic segmentation with uncertainty-guided self cross supervision

2022-03-10 · Yunyang Zhang, Zhiqiang Gong, Xiaohu Zheng, Xiaoyu Zhao 외

As a powerful way of realizing semi-supervised segmentation, the cross supervision method learns cross consistency based on independent ensemble models using abundant unlabeled images. However, the wrong pseudo labeling …

SegmentationSemantic Segmentation

K-spin Hamiltonian for quantum-resolvable Markov decision processes

2020-04-13 · Eric B. Jones, Peter Graf, Eliot Kapit, Wesley Jones

The Markov decision process is the mathematical formalization underlying the modern field of reinforcement learning when transition and reward functions are unknown. We derive a pseudo-Boolean cost function that is equiv…

Q-LearningReinforcement LearningReinforcement Learning (RL)

A formal approach to good practices in Pseudo-Labeling for Unsupervised Domain Adaptive Re-Identification

2021-12-24 · Fabian Dubourvieux, Romaric Audigier, Angélique Loesch, Samia Ainouz 외

The use of pseudo-labels prevails in order to tackle Unsupervised Domain Adaptive (UDA) Re-Identification (re-ID) with the best performance. Indeed, this family of approaches has given rise to several UDA re-ID specific …

Refined Pseudo labeling for Source-free Domain Adaptive Object Detection

2023-03-07 · Siqi Zhang, Lu Zhang, Zhiyong Liu

Domain adaptive object detection (DAOD) assumes that both labeled source data and unlabeled target data are available for training, but this assumption does not always hold in real-world scenarios. Thus, source-free DAOD…

object-detectionObject DetectionPseudo Label

MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning

2025-05-22 · Zihan Chen, Song Wang, Zhen Tan, Jundong Li 외

In-Context Learning (ICL) empowers Large Language Models (LLMs) to tackle diverse tasks by incorporating multiple input-output examples, known as demonstrations, into the input of LLMs. More recently, advancements in the…

In-Context Learning