Stroke remains the second - leading cause of death globally and the primary driver of long - term neurological disabilities, significantly impacting quality of life (Yüksel et al., 2023). It ranks among the top three contributors to disability - adjusted life ye ars (DALYs) lost worldwide, particularly within musculoskeletal and neurological disorders. Cerebrovascular diseases (CVDs), which manifest as strokes, are a major source of morbidity and mortality, affecting approximately 15 million individuals annually -- 5 million of whom face chronic paralysis (Organization, 2015; Polat et al., 2024). These conditions stem from disruptions in cerebral blood flow, leading to pathologies such as ischemic strokes, hemorrhages, and traumatic brain injuries due to vascular dama ge (Goni et al., 2022). Strokes are categorized into two distinct types: Ischemic Stroke: Caused by thrombotic or embolic blockages in cerebral arteries, resulting in hypoxic necrosis of brain tissue (Zhu et al., 2024).

Abstract--AI-powered drug discovery typically relies on the successful prediction of compound-protein interactions, which are pivotal for the evaluation of designed compound molecules in structure-based drug design and represent a core challenge in the field. However, accurately predicting compound-protein affinity via regression models usually requires adequate-binding pose, which are derived from costly and complex experimental methods or time-consuming simulations with docking software. In response, we have introduced the GenShin model, which constructs a geometry-enhanced structural graph module that separately extracts additional features from proteins and compounds. Consequently, it attains an accuracy on par with mainstream models in predicting compound-protein affinities, while eliminating the need for adequate-binding pose as input. Our experimental findings demonstrate that the GenShin model vastly outperforms other models that rely on non-input docking conformations, achieving, or in some cases even exceeding, the performance of those requiring adequate-binding pose. Further experiments indicate that our GenShin model is more robust to inadequate-binding pose, affirming its higher suitability for real-world drug discovery scenarios. We hope our work will inspire more endeavors to bridge the gap between AI models and practical drug discovery challenges. Currently, compound-protein binding affinity can be measured via various experimental techniques, including isothermal titration calorimetry (ITC) [1] and surface plasmon resonance (SPR) [2]. Y et, these traditional methods are both time-intensive and costly .

--In recent years, Graph Convolutional Networks (GCNs) have gained popularity for their exceptional ability to process graph-structured data. Existing GCN-based approaches typically employ a shallow model architecture due to the over-smoothing phenomenon. Current approaches to mitigating over-smoothing primarily involve adding supplementary components to GCN architectures, such as residual connections and random edge-dropping strategies. However, these improvements toward deep GCNs have achieved only limited success. In this work, we analyze the intrinsic message passing mechanism of GCNs and identify a critical issue: messages originating from high-order neighbors must traverse through low-order neighbors to reach the target node. This repeated reliance on low-order neighbors leads to redundant information aggregation, a phenomenon we term over-aggregation. Our analysis demonstrates that over-aggregation not only introduces significant redundancy but also serves as the fundamental cause of over-smoothing in GCNs. Motivated by this discovery, we introduce a novel framework named redundancy-free graph convolutional network, where the neighbors of the graph are hierarchically organized so that the multi-order neighbor sets of a specific node do not intersect. This organizational structure enables high-order neighbors to directly propagate their messages to the target node, thereby effectively avoiding duplicate aggregation. The layer number of the proposed method adapts according to the graph structure, eliminating the need for manual adjustments to capture node information at specific distances. The experimental results on sixteen real-world datasets demonstrate the superior performance of the proposed method on node-and graph-level tasks.

Causal analysis plays a foundational role in scientific discovery and reliable decision-making, yet it remains largely inaccessible to domain experts due to its conceptual and algorithmic complexity. This disconnect between causal methodology and practical usability presents a dual challenge: domain experts are unable to leverage recent advances in causal learning, while causal researchers lack broad, real-world deployment to test and refine their methods. To address this, we introduce Causal-Copilot, an autonomous agent that operationalizes expert-level causal analysis within a large language model framework. Causal-Copilot automates the full pipeline of causal analysis for both tabular and time-series data -- including causal discovery, causal inference, algorithm selection, hyperparameter optimization, result interpretation, and generation of actionable insights. It supports interactive refinement through natural language, lowering the barrier for non-specialists while preserving methodological rigor. By integrating over 20 state-of-the-art causal analysis techniques, our system fosters a virtuous cycle -- expanding access to advanced causal methods for domain experts while generating rich, real-world applications that inform and advance causal theory. Empirical evaluations demonstrate that Causal-Copilot achieves superior performance compared to existing baselines, offering a reliable, scalable, and extensible solution that bridges the gap between theoretical sophistication and real-world applicability in causal analysis. A live interactive demo of Causal-Copilot is available at https://causalcopilot.com/.

As machine learning models are increasingly used in educational settings, from detecting at-risk students to predicting student performance, algorithmic bias and its potential impacts on students raise critical concerns about algorithmic fairness. Although group fairness is widely explored in education, works on individual fairness in a causal context are understudied, especially on counterfactual fairness. This paper explores the notion of counterfactual fairness for educational data by conducting counterfactual fairness analysis of machine learning models on benchmark educational datasets. We demonstrate that counterfactual fairness provides meaningful insight into the causality of sensitive attributes and causal-based individual fairness in education.

A BSTRACT In the era of data expansion, ensuring data privacy has become increasingly critical, posing significant challenges to traditional AI-based applications. In addition, the increasing adoption of IoT devices has introduced significant cybersecurity challenges, making traditional Network Intrusion Detection Systems (NIDS) less effective against evolving threats, and privacy concerns and regulatory restrictions limit their deployment. Federated Learning (FL) has emerged as a promising solution, allowing decentralized model training while maintaining data privacy to solve these issues. However, despite implementing privacy-preserving technologies, FL systems remain vulnerable to adversarial attacks. Furthermore, data distribution among clients is not heterogeneous in the FL scenario. We propose WeiDetect, a two-phase, server-side defense mechanism for FL-based NIDS that detects malicious participants to address these challenges. In the first phase, local models are evaluated using a validation dataset to generate validation scores. These scores are then analyzed using a Weibull distribution, identifying and removing malicious models. We conducted experiments to evaluate the effectiveness of our approach in diverse attack settings. Our evaluation included two popular datasets, CIC-Darknet2020 and CSE-CIC-IDS2018, tested under non-IID data distributions. Our findings highlight that WeiDetect outperforms state-of-the-art defense approaches, improving higher target class recall up to 70% and enhancing the global model's F1 score by 1% to 14%. K eywords Federated learning Poisoning attacks Network intrusion detection systems Non-independent and identically distributed data Weibull distribution 1 Introduction The rapid advancement of the Internet has created a highly interconnected world. The adoption of IoT for connectivity has increased significantly, leading to security vulnerabilities due to the inherent nature of IoT devices and systems. According to [1], it was emphasized that IoT devices are expected to reach 55.7 billion by 2025; the increasing volume of data generated by these devices also opens the door to cyber attackers. This further signifies the critical role of the Network Intrusion Detection System (NIDS), which detects suspicious activities and improves the security of the IoT network ecosystem. The NIDS employs signature, behavior, or specification-based approaches to identify network anomalies and protect the system from unauthorized use or access [2]. However, these approaches have become less efficient in recognizing unknown attacks, rendering them incapable of detecting new or evolving threats. The paper [3, 4] highlight that Machine Learning (ML) based NIDSs are efficient alternatives that identify normal and abnormal traffic patterns in IoT Corresponding author: vinod.puthuvath@unipd.it Although these ML models have been widely employed in various solutions to enable dynamic and adaptive IDS in IoT environments.

This thesis employs a hybrid CNN-Transformer architecture, alongside a detailed anthropological framework, to investigate potential historical connections between the visual morphology of the Indus Valley script and pictographic systems of the Tibetan-Yi Corridor. Through an ensemble methodology of three target scripts across 15 independently trained models, we demonstrate that Tibetan-Yi Corridor scripts exhibit approximately six-fold higher visual similarity to the Indus script (0.635) than to the Bronze Age Proto-Cuneiform (0.102) or Proto-Elamite (0.078). Contrary to expectations, when measured through direct script-to-script embedding comparisons, the Indus script maps closer to Tibetan-Yi Corridor scripts with a mean cosine similarity of 0.930 (CI: [0.917, 0.942]) than to contemporaneous West Asian signaries, which recorded mean similarities of 0.887 (CI: [0.863, 0.911]) and 0.855 (CI: [0.818, 0.891]). Across dimensionality reduction and clustering methods, the Indus script consistently clusters closest to Tibetan-Yi Corridor scripts. These computational findings align with observed pictorial parallels in numeral systems, gender markers, and iconographic elements. Archaeological evidence of contact networks along the ancient Shu-Shendu road, coinciding with the Indus Civilization's decline, provides a plausible transmission pathway. While alternate explanations cannot be ruled out, the specificity and consistency of similarities suggest more complex cultural transmission networks between South and East Asia than previously recognized.

In recent years, representation learning has become the research focus of the machine learning community. Large-scale neural networks are a crucial step toward achieving general intelligence, with their success largely attributed to their ability to learn abstract representations of data. Several learning fields are actively discussing how to learn representations, yet there is a lack of a unified perspective. We convert the representation learning problem under different tasks into a ranking problem. By adopting the ranking problem as a unified perspective, representation learning tasks can be solved in a unified manner by optimizing the ranking loss. Experiments under various learning tasks, such as classification, retrieval, multi-label learning, and regression, prove the superiority of the representation learning by ranking framework. Furthermore, experiments under self-supervised learning tasks demonstrate the significant advantage of the ranking framework in processing unsupervised training data, with data augmentation techniques further enhancing its performance.

We study the algorithmic task of learning Boolean disjunctions in the distribution-free agnostic PAC model. The best known agnostic learner for the class of disjunctions over $\{0, 1\}^n$ is the $L_1$-polynomial regression algorithm, achieving complexity $2^{\tilde{O}(n^{1/2})}$. This complexity bound is known to be nearly best possible within the class of Correlational Statistical Query (CSQ) algorithms. In this work, we develop an agnostic learner for this concept class with complexity $2^{\tilde{O}(n^{1/3})}$. Our algorithm can be implemented in the Statistical Query (SQ) model, providing the first separation between the SQ and CSQ models in distribution-free agnostic learning.

Bayesian Federated Learning (BFL) enables uncertainty quantification and robust adaptation in distributed learning. In contrast to the frequentist approach, it estimates the posterior distribution of a global model, offering insights into model reliability. However, current BFL methods neglect continual learning challenges in dynamic environments where data distributions shift over time. We propose a continual BFL framework applied to human sensing with radar data collected over several days. Using Stochastic Gradient Langevin Dynamics (SGLD), our approach sequentially updates the model, leveraging past posteriors to construct the prior for the new tasks. We assess the accuracy, the expected calibration error (ECE) and the convergence speed of our approach against several baselines. Results highlight the effectiveness of continual Bayesian updates in preserving knowledge and adapting to evolving data.