IEEE

ATFSAD: Enhancing Long Sequence Time-Series Forecasting on Air Temperature Prediction

Abstract: Long sequence time-series forecasting models pay excessive attention to irrelevant information and noise when predicting air temperature, leading to prediction drift and poor generalization ...
GitHub

Deep learning models for traffic prediction

ACFM ACFM: A Dynamic Spatial-Temporal Network for Traffic Prediction Pytorch ACM MM2018/A STDN Revisiting spatial-temporal similarity: A deep learning framework for traffic prediction Keras AAAI2019/A ...
IEEE

Rethinking Link Prediction for Directed Graphs

Abstract: Link prediction for directed graphs is a crucial task with diverse real-world applications. Recent advances in embedding methods and Graph Neural Networks (GNNs) have shown promising ...

训检索器还在苦哈哈标正负样本?DREAM:让大模型自己“猜答案“就够了

DREAM 证明了你根本不需要任何人工标注的正负样本,只凭"一篇文档能不能帮大模型预测出正确答案"这一个信号,就能把稠密检索器训得很强;而它的关键诀窍,是把检索器算出的相似度分数注入到冻结大模型里那些"本来就在替 query 寻找相关内容"的注意力头中,让下一个词预测的损失顺着注意力这条路反向把检索器调教出来。 一、研究背景:有没有可能,不标一条数据就把检索器练强? 先说清楚这篇论文在解决什么。稠 ...
Frontiers

Combining machine learning and physiological network models for sepsis prediction

Self-Organization of Complex Physiological Networks: Synergetic Principles and Applications — In Memory of Hermann Haken ...
GitHub

Trustworthy-AI-Group/Adversarial_Examples_Papers

Sayeed Shafayet Chowdhury, Md. Shaown Miah Adversarially Robust Control of Conditional Value-at-Risk via Rockafellar-Uryasev Conformal Inference Catherine Chen, Jingyan Shen, Zhun Deng, Lihua Lei ...
NPR

Cristina Kim

Cristina Kim is a reporter/producer for Throughline. Before joining NPR, Kim was the race and equity reporter at KPBS in San Diego where she covered housing, evictions, and the racial wealth gap. Her ...