Patterns最新文献

As the parameter size of large language models (LLMs) continues to expand, there is an urgent need to address the scarcity of high-quality data. In response, existing research has attempted to make a breakthrough by incorporating federated learning (FL) into LLMs. Conversely, considering the outstanding performance of LLMs in task generalization, researchers have also tried applying LLMs within FL to tackle challenges in relevant domains. The complementarity between LLMs and FL has already ignited widespread research interest. In this review, we aim to deeply explore the integration of LLMs and FL. We propose a research framework dividing the fusion of LLMs and FL into three parts: the combination of LLM sub-technologies with FL, the integration of FL sub-technologies with LLMs, and the overall merger of LLMs and FL. We first provide a comprehensive review of the current state of research in the domain of LLMs combined with FL, including their typical applications, integration advantages, challenges faced, and future directions for resolution. Subsequently, we discuss the practical applications of the combination of LLMs and FL in critical scenarios such as healthcare, finance, and education and provide new perspectives and insights into future research directions for LLMs and FL.

Modern intelligent engineering and management scenarios require advanced data utilization methodologies. Here, we propose and discuss data-knowledge co-driven innovations that could address emerging challenges, and we advocate for the adoption of interdisciplinary methodologies in numerous engineering and management applications.

To achieve adequate trust in patient-critical medical tasks, artificial intelligence must be able to recognize instances where they cannot operate confidently. Ensemble methods are deployed to estimate uncertainty, but models in an ensemble often share the same vulnerabilities to adversarial attacks. We propose an ensemble approach based on feature decorrelation and Fourier partitioning for teaching networks diverse features, reducing the chance of perturbation-based fooling. We test our approach against white-box attacks in single- and multi-channel electrocardiogram classification and adapt adversarial training and DVERGE into an ensemble framework for comparison. Our results indicate that the combination of decorrelation and Fourier partitioning maintains performance on unperturbed data while demonstrating superior uncertainty estimation on projected gradient descent and smooth adversarial attacks of various magnitudes. Furthermore, our approach does not require expensive optimization with adversarial samples during training. These methods can be applied to other tasks for more robust models.

Guidelines in statistical modeling for genomics hold that simpler models have advantages over more complex ones. Potential advantages include cost, interpretability, and improved generalization across datasets or biological contexts. We directly tested the assumption that small gene signatures generalize better by examining the generalization of mutation status prediction models across datasets (from cell lines to human tumors and vice versa) and biological contexts (holding out entire cancer types from pan-cancer data). We compared model selection between solely cross-validation performance and combining cross-validation performance with regularization strength. We did not observe that more regularized signatures generalized better. This result held across both generalization problems and for both linear models (LASSO logistic regression) and non-linear ones (neural networks). When the goal of an analysis is to produce generalizable predictive models, we recommend choosing the ones that perform best on held-out data or in cross-validation instead of those that are smaller or more regularized.

This article examines the convergence of physics, chemistry, and artificial intelligence (AI), highlighted by recent Nobel Prizes. It traces the historical development of neural networks, emphasizing interdisciplinary research's role in advancing AI. The authors advocate for nurturing AI-enabled polymaths to bridge the gap between theoretical advancements and practical applications, driving progress toward artificial general intelligence (AGI).

The placenta is vital to maternal and child health but often overlooked in pregnancy studies. Addressing the need for a more accessible and cost-effective method of placental assessment, our study introduces a computational tool designed for the analysis of placental photographs. Leveraging images and pathology reports collected from sites in the United States and Uganda over a 12-year period, we developed a cross-modal contrastive learning algorithm consisting of pre-alignment, distillation, and retrieval modules. Moreover, the proposed robustness evaluation protocol enables statistical assessment of performance improvements, provides deeper insight into the impact of different features on predictions, and offers practical guidance for its application in a variety of settings. Through extensive experimentation, our tool demonstrates an average area under the receiver operating characteristic curve score of over 82% in both internal and external validations, which underscores the potential of our tool to enhance clinical care across diverse environments.

Hou and He et al.¹ developed a new RNA virus identification tool named LucaProt, a transformer-based bioinformatics software using sequence and structural characteristics of RNA-dependent RNA polymerases (RdRPs), which are essential for almost all RNA viruses. LucaProt can identify RdRPs from highly diverse RNA viruses, unveiling the hidden RNA virosphere.

In this opinion piece, the authors, from the fields of artificial intelligence (AI) and psychology, reflect on how the foundational discoveries of Nobel laureates Hopfield and Hinton have influenced their research. They also discuss emerging directions in AI and the challenges that lie ahead for neural networks and machine learning.

The possibility that single-cell gene expression datasets could leak information about individuals' genotypes has been largely unexplored. Walker et al. showed that even noisy genotype predictions derived from these data can be linked to the corresponding genotype profiles with significant accuracy.

Digital research infrastructure (DRI) for environmental science requires significant transformation to support the changing nature of science and utilize digital innovations. Numerous challenges prevent this change yet simultaneously pose exciting principles to drive the future of DRI. This opinion piece details a multi-dimensional approach toward these futures for the environmental community.