Diabetes mellitus (DM) is a global health issue of significance that must be diagnosed as early as possible and managed well. This study presents a framework for diabetes prediction using Machine Learning (ML) models, complemented with eXplainable Artificial Intelligence (XAI) tools, to investigate both the predictive accuracy and interpretability of the predictions from ML models. Data Preprocessing is based on the Synthetic Minority Oversampling Technique (SMOTE) and feature scaling used on the Diabetes Binary Health Indicators dataset to deal with class imbalance and variability of clinical features. The ensemble model provided high accuracy, with a test accuracy of 92.50% and an ROC-AUC of 0.975. BMI, Age, General Health, Income, and Physical Activity were the most influential predictors obtained from the model explanations. The results of this study suggest that ML combined with XAI is a promising means of developing accurate and computationally transparent tools for use in healthcare systems.

Single-nucleus RNA sequencing (snRNA-seq) has significantly advanced our understanding of the disease etiology of neurodegenerative disorders. However, the low quality of specimens derived from postmortem brain tissues, combined with the high variability caused by disease heterogeneity, makes it challenging to integrate snRNA-seq data from multiple sources for precise analyses. To address these challenges, we present scMamba, a pre-trained model designed to improve the quality and utility of snRNA-seq analysis, with a particular focus on neurodegenerative diseases. Inspired by the recent Mamba model, scMamba introduces a novel architecture that incorporates a linear adapter layer, gene embeddings, and bidirectional Mamba blocks, enabling efficient processing of snRNA-seq data while preserving information from the raw input. Notably, scMamba learns generalizable features of cells and genes through pre-training on snRNA-seq data, without relying on dimension reduction or selection of highly variable genes. We demonstrate that scMamba outperforms benchmark methods in various downstream tasks, including cell type annotation, doublet detection, imputation, and the identification of differentially expressed genes.

STRONG POINTS/CONTRIBUTIONS 1) The false positive rates and false negative rates observed when using AutoPerf are impressively low. NEGATIVE POINTS 1) The paper lacks a lot of technical depth and novelty… autoencoders for anomaly detection are widely used, and the problem domain (detecting performance bugs) has been studied previously as well. Knowing what was changed in the code between P_i and P_i 1 could be very, very helpful. DETAILED COMMENTS One comment is that I'm not sure it makes a lot of sense to train separate autoencoders for each function (or group of functions, if you are doing the k-means thing). Likely, there are going to be certain characteristics of the distributions that are shares across all functions, and I worry that you are wasting a lot of compute power by relearning everything.

In discrete undirected graphical models, the conditional independence of node labels Y is specified by the graph structure. We study the case where there is another input random vector X (e.g.

Recent studies attempt to optimize maintain acceptable error rates in the face of massive-scale networks sketches using machine learning; however, these approaches and highly skewed traffic distributions [7, 15]. In practice, a face the challenges of lacking adaptivity to dynamic networks and small fraction of large flows typically accounts for the majority of incurring high training costs. In this paper, we propose LLM-Sketch, total traffic volume, while many small flows remain numerous yet based on the insight that fields beyond the flow IDs in packet headers contribute only modestly. A representative example is the Count-can also help infer flow sizes. By using a two-tier data structure Min Sketch (CMS) [12], which updates and queries counters based and separately recording large and small flows, LLM-Sketch improves on hashed flow IDs. Although CMS is simple and memory-efficient, accuracy while minimizing memory usage. Furthermore, it it faces a fundamental trade-off: counters sized for small flows undercount leverages fine-tuned large language models (LLMs) to reliably estimate the large ones, while counters sized for large flows waste flow sizes. We evaluate LLM-Sketch on three representative memory on the many small ones. Consequently, CMS cannot accurately tasks, and the results demonstrate that LLM-Sketch outperforms capture the minority of large flows without significantly state-of-the-art methods by achieving a 7.5 accuracy improvement.

Classification is a ubiquitous and fundamental problem in artificial intelligence and machine learning, with extensive efforts dedicated to developing more powerful classifiers and larger datasets. However, the classification task is ultimately constrained by the intrinsic properties of datasets, independently of computational power or model complexity. In this work, we introduce a formal entropy-based measure of classificability, which quantifies the inherent difficulty of a classification problem by assessing the uncertainty in class assignments given feature representations. This measure captures the degree of class overlap and aligns with human intuition, serving as an upper bound on classification performance for classification problems. Our results establish a theoretical limit beyond which no classifier can improve the classification accuracy, regardless of the architecture or amount of data, in a given problem. Our approach provides a principled framework for understanding when classification is inherently fallible and fundamentally ambiguous.

In typical use-cases, existing methods focus on Harmlessness and Persistence (Xu et al., 2024a; Russinovich & Model fingerprinting has emerged as a powerful Salem, 2024) of fingerprints. Fingerprinting is Harmless if tool for model owners to identify their shared the utility of the fingerprinted model does not degrade from model given API access. However, to lower false the base model, and it is Persistent if performing supervised discovery rate, fight fingerprint leakage, and defend fine-tuning (SFT) on the fingerprinted model with other data against coalitions of model users attempting does not make model forget the fingerprints (Jagielski et al., to bypass detection, we argue that scalability is 2023; Chen et al., 2024). While these properties are important, critical, i.e., scaling up the number of fingerprints we argue that there is another important criterion for one can embed into a model. Hence, we pose a good fingerprinting scheme not captured by prior work: scalability as a crucial requirement for fingerprinting Scalability. A fingerprinting scheme is scalable if many schemes. We experiment with fingerprint design fingerprints can be added without hurting the performance at a scale significantly larger than previously of the model.

The goal of bacterial genome-wide association studies (bGWAS) is to identify genetic variants that influence a trait or phenotype ([31]). These studies traditionally employ statistical methods to perform population genomic analyses to yield a list of candidate genes or genetic markers associated with a phenotype, and have been a significant contributor in uncovering numerous genetic loci that are causally related to a phenotype, e.g., resistance to an antibiotic ([8, 15, 19, 10, 4]). Improvements in whole-genome sequencing techniques have led to the generation of increasing amounts of data, creating an impracticality surrounding functional investigations of all loci individually. However, this up-scaling has lead to the prediction of a greater number of significantly associated loci despite efforts to minimize false discovery rate. Machine learning (ML) algorithms are an obvious successor to bGWAS that may more effectively find signal in genetic noise. To date, existing algorithms have been applied to the data with little to no adaptation ([34, 26, 9, 33]). Researchers are finding that these ML models fail to reliably generalize to out-of-distribution examples ([7], [14]), and frequently identify false positive associations ([26]). In addition, they have found that removing all known causal variables from a model does not meaningfully impact model accuracy ([25]).

The interactions between DNA, RNA, and proteins are fundamental to biological processes, as illustrated by the central dogma of molecular biology. While modern biological pre-trained models have achieved great success in analyzing these macromolecules individually, their interconnected nature remains under-explored. In this paper, we follow the guidance of the central dogma to redesign both the data and model pipeline and offer a comprehensive framework, Life-Code, that spans different biological functions. As for data flow, we propose a unified pipeline to integrate multi-omics data by reverse-transcribing RNA and reverse-translating amino acids into nucleotide-based sequences. As for the model, we design a codon tokenizer and a hybrid long-sequence architecture to encode the interactions of both coding and non-coding regions with masked modeling pre-training. To model the translation and folding process with coding sequences, Life-Code learns protein structures of the corresponding amino acids by knowledge distillation from off-the-shelf protein language models. Such designs enable Life-Code to capture complex interactions within genetic sequences, providing a more comprehensive understanding of multi-omics with the central dogma. Extensive Experiments show that Life-Code achieves state-of-the-art performance on various tasks across three omics, highlighting its potential for advancing multi-omics analysis and interpretation.

Federated Distillation (FD) has emerged as a popular federated training framework, enabling clients to collaboratively train models without sharing private data. Public Dataset-Assisted Federated Distillation (PDA-FD), which leverages public datasets for knowledge sharing, has become widely adopted. Although PDA-FD enhances privacy compared to traditional Federated Learning, we demonstrate that the use of public datasets still poses significant privacy risks to clients' private training data. This paper presents the first comprehensive privacy analysis of PDA-FD in presence of an honest-but-curious server. We show that the server can exploit clients' inference results on public datasets to extract two critical types of private information: label distributions and membership information of the private training dataset. To quantify these vulnerabilities, we introduce two novel attacks specifically designed for the PDA-FD setting: a label distribution inference attack and innovative membership inference methods based on Likelihood Ratio Attack (LiRA). Through extensive evaluation of three representative PDA-FD frameworks (FedMD, DS-FL, and Cronus), our attacks achieve state-of-the-art performance, with label distribution attacks reaching minimal KL-divergence and membership inference attacks maintaining high True Positive Rates under low False Positive Rate constraints. Our findings reveal significant privacy risks in current PDA-FD frameworks and emphasize the need for more robust privacy protection mechanisms in collaborative learning systems.