A review on machine learning, artificial intelligence, and smart technology in water treatment and monitoring

M Lowe, R Qin, X Mao - Water, 2022 - mdpi.com
Artificial-intelligence methods and machine-learning models have demonstrated their ability
to optimize, model, and automate critical water-and wastewater-treatment applications …

Emergence and causality in complex systems: a survey of causal emergence and related quantitative studies

B Yuan, J Zhang, A Lyu, J Wu, Z Wang, M Yang, K Liu… - Entropy, 2024 - mdpi.com
Emergence and causality are two fundamental concepts for understanding complex
systems. They are interconnected. On one hand, emergence refers to the phenomenon …

Towards out-of-distribution generalization: A survey

J Liu, Z Shen, Y He, X Zhang, R Xu, H Yu… - arxiv preprint arxiv …, 2021 - arxiv.org
Traditional machine learning paradigms are based on the assumption that both training and
test data follow the same statistical pattern, which is mathematically referred to as …

Alleviating structural distribution shift in graph anomaly detection

Y Gao, X Wang, X He, Z Liu, H Feng… - Proceedings of the …, 2023 - dl.acm.org
Graph anomaly detection (GAD) is a challenging binary classification problem due to its
different structural distribution between anomalies and normal nodes---abnormal nodes are …

Out-of-distribution generalization with causal invariant transformations

R Wang, M Yi, Z Chen, S Zhu - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
In real-world applications, it is important and desirable to learn a model that performs well on
out-of-distribution (OOD) data. Recently, causality has become a powerful tool to tackle the …

Learning to reweight for generalizable graph neural network

Z Chen, T **ao, K Kuang, Z Lv, M Zhang… - Proceedings of the …, 2024 - ojs.aaai.org
Graph Neural Networks (GNNs) show promising results for graph tasks. However, existing
GNNs' generalization ability will degrade when there exist distribution shifts between testing …

Out-of-distribution generalization with causal feature separation

H Wang, K Kuang, L Lan, Z Wang… - … on Knowledge and …, 2023 - ieeexplore.ieee.org
Driven by empirical risk minimization, machine learning algorithm tends to exploit subtle
statistical correlations existing in the training environment for prediction, while the spurious …

Uncovering main causalities for long-tailed information extraction

G Nan, J Zeng, R Qiao, Z Guo, W Lu - arxiv preprint arxiv:2109.05213, 2021 - arxiv.org
Information Extraction (IE) aims to extract structural information from unstructured texts. In
practice, long-tailed distributions caused by the selection bias of a dataset, may lead to …

A survey on evaluation of out-of-distribution generalization

H Yu, J Liu, X Zhang, J Wu, P Cui - arxiv preprint arxiv:2403.01874, 2024 - arxiv.org
Machine learning models, while progressively advanced, rely heavily on the IID assumption,
which is often unfulfilled in practice due to inevitable distribution shifts. This renders them …

A Unified Invariant Learning Framework for Graph Classification

Y Sui, J Sun, S Wang, Z Liu, Q Cui, L Li… - arxiv preprint arxiv …, 2025 - arxiv.org
Invariant learning demonstrates substantial potential for enhancing the generalization of
graph neural networks (GNNs) with out-of-distribution (OOD) data. It aims to recognize …