Your Next State-of-the-Art Could Come from Another Domain: A Cross-Domain Analysis of Hierarchical Text Classification [0.03%]
下一个最先进的方法可能来自另一个领域——层次文本分类的跨领域分析
Nan Li,Bo Kang,Tijl De Bie
Nan Li
Text classification with hierarchical labels is a prevalent and challenging task in natural language processing. Examples include assigning ICD codes to patient records, tagging patents with IPC classes, assigning EUROVOC descriptors to Eur...
Zhigao Guo,Feng Dong
Zhigao Guo
Incorporating causal knowledge and mechanisms is essential for refining causal models and improving downstream tasks, such as designing new treatments. In this paper, we introduce a novel concept in causal discovery, termed interventional c...
Boolean matrix logic programming for active learning of gene functions in genome-scale metabolic network models [0.03%]
基于基因组规模代谢网络模型主动学习基因功能的布尔矩阵逻辑编程方法研究
Lun Ai,Stephen H Muggleton,Shi-Shun Liang et al.
Lun Ai et al.
Reasoning about hypotheses and updating knowledge through empirical observations are central to scientific discovery. In this work, we applied logic-based machine learning methods to drive biological discovery by guiding experimentation. Ge...
Martin Atzmueller,Carolina Centeio Jorge,Cláudio Rebelo de Sá et al.
Martin Atzmueller et al.
Social interactions are prevalent in our lives. These can be observed, e. g., online using social media, however, also offline specifically using sensors. In such contexts, typically time-stamped interactions are recorded, which can also be...
Persistent Laplacian-enhanced algorithm for scarcely labeled data classification [0.03%]
持久拉普拉斯增强算法在少量标记数据分类中的应用
Gokul Bhusal,Ekaterina Merkurjev,Guo-Wei Wei
Gokul Bhusal
The success of many machine learning (ML) methods depends crucially on having large amounts of labeled data. However, obtaining enough labeled data can be expensive, time-consuming, and subject to ethical constraints for many applications. ...
Ensuring medical AI safety: interpretability-driven detection and mitigation of spurious model behavior and associated data [0.03%]
确保医学AI的安全性：通过可解释性驱动检测和缓解模型异常行为及相应数据偏差
Frederik Pahde,Thomas Wiegand,Sebastian Lapuschkin et al.
Frederik Pahde et al.
Deep neural networks are increasingly employed in high-stakes medical applications, despite their tendency for shortcut learning in the presence of spurious correlations, which can have potentially fatal consequences in practice. Whereas a ...
Xin Ma,Suprateek Kundu,Jennifer Stevens
Xin Ma
Although there has been an explosive rise in network data in a variety of disciplines, there is very limited development of regression modeling approaches based on high-dimensional networks. The scarce literature in this area typically assu...
Henri Schmidt,Christian Düll
Henri Schmidt
We provide an implementation to compute the flat metric in any dimension. The flat metric, also called dual bounded Lipschitz distance, generalizes the well-known Wasserstein distance W 1 to the case that the distributions are of unequal t...
Deep latent force models: ODE-based process convolutions for Bayesian deep learning [0.03%]
基于ODE的过程卷积的深度潜在力模型：贝叶斯深度学习
Thomas Baldwin-McDonald,Xinxing Shi,Mingxin Shen et al.
Thomas Baldwin-McDonald et al.
Modelling the behaviour of highly nonlinear dynamical systems with robust uncertainty quantification is a challenging task which typically requires approaches specifically designed to address the problem at hand. We introduce a domain-agnos...
Offline reinforcement learning for learning to dispatch for job shop scheduling [0.03%]
离线强化学习在作业车间调度中的应用研究
Jesse van Remmerden,Zaharah Bukhsh,Yingqian Zhang
Jesse van Remmerden
The Job Shop Scheduling Problem (JSSP) is a complex combinatorial optimization problem. While online Reinforcement Learning (RL) has shown promise by quickly finding acceptable solutions for JSSP, it faces key limitations: it requires exten...