Anxiety is endemic to every person, with an occurrence rate of approximately 20% [World Health Organization, 2017]. Between 2020 and 2022, over one in six people (17.2% or 3.4 million people) aged 16 to 85 years experienced an anxiety disorder [Australian Bureau of Statistics]. Anxiety is caused by changes in the situation, nervousness and common symptoms, including sweating, trembling and excessive worrying, which affect a person's daily life. Anxiety disorders encompass a range of conditions, such as generalised anxiety disorder (GAD), panic disorder (PD), social anxiety disorder (SAD), obsessive-compulsive disorder (OCD), various phobia-related disorders, physical pain related protective behaviour [Li et al., 2020, 2021] and depression [Ghosh and Anwar, 2021]. Current clinical approaches for diagnosing these disorders often suffer from limitations in accuracy and objectivity, relying heavily on self-reports, patient histories and clinical observations. These methods can be subjective and may not capture the nuanced neural and behavioural patterns associated with anxiety, leading to potential misdiagnoses. Recent research has shown promising results in using machine learning techniques to detect anxiety through physiological analysis [Abd-Alrazaq et al., 2023], such as respiration, electrocardiogram (ECG), photoplethysmography (PPG), electrodermal response (EDA) and electroencephalography (EEG), to identify patterns associated with anxiety states [Abd-Alrazaq et al., 2023].

Self-supervised speech representation learning has become essential for extracting meaningful features from untranscribed audio. Recent advances highlight the potential of deriving discrete symbols from the features correlated with linguistic units, which enables text-less training across diverse tasks. In particular, sentence-level Self-Distillation of the pretrained HuBERT (SD-HuBERT) induces syllabic structures within latent speech frame representations extracted from an intermediate Transformer layer. In SD-HuBERT, sentence-level representation is accumulated from speech frame features through self-attention layers using a special CLS token. However, we observe that the information aggregated in the CLS token correlates more with speaker identity than with linguistic content. To address this, we propose a speech-only self-supervised fine-tuning approach that separates syllabic units from speaker information. Our method introduces speaker perturbation as data augmentation and adopts a frame-level training objective to prevent the CLS token from aggregating paralinguistic information. Experimental results show that our approach surpasses the current state-of-the-art method in most syllable segmentation and syllabic unit quality metrics on Librispeech, underscoring its effectiveness in promoting syllabic organization within speech-only models.

Forecasting the future trajectories of surrounding agents is crucial for autonomous vehicles to ensure safe, efficient, and comfortable route planning. While model ensembling has improved prediction accuracy in various fields, its application in trajectory prediction is limited due to the multi-modal nature of predictions. In this paper, we propose a novel sampling method applicable to trajectory prediction based on the predictions of multiple models. We first show that conventional sampling based on predicted probabilities can degrade performance due to missing alignment between models. To address this problem, we introduce a new method that generates optimal trajectories from a set of neural networks, framing it as a risk minimization problem with a variable loss function. By using state-of-the-art models as base learners, our approach constructs diverse and effective ensembles for optimal trajectory sampling. Extensive experiments on the nuScenes prediction dataset demonstrate that our method surpasses current state-of-the-art techniques, achieving top ranks on the leaderboard. We also provide a comprehensive empirical study on ensembling strategies, offering insights into their effectiveness. Our findings highlight the potential of advanced ensembling techniques in trajectory prediction, significantly improving predictive performance and paving the way for more reliable predicted trajectories.

Modeling spatiotemporal interactions in multivariate time series is key to their effective processing, but challenging because of their irregular and often unknown structure. Statistical properties of the data provide useful biases to model interdependencies and are leveraged by correlation and covariance-based networks as well as by processing pipelines relying on principal component analysis (PCA). However, PCA and its temporal extensions suffer instabilities in the covariance eigenvectors when the corresponding eigenvalues are close to each other, making their application to dynamic and streaming data settings challenging. To address these issues, we exploit the analogy between PCA and graph convolutional filters to introduce the SpatioTemporal coVariance Neural Network (STVNN), a relational learning model that operates on the sample covariance matrix of the time series and leverages joint spatiotemporal convolutions to model the data. To account for the streaming and non-stationary setting, we consider an online update of the parameters and sample covariance matrix. We prove the STVNN is stable to the uncertainties introduced by these online estimations, thus improving over temporal PCA-based methods. Experimental results corroborate our theoretical findings and show that STVNN is competitive for multivariate time series processing, it adapts to changes in the data distribution, and it is orders of magnitude more stable than online temporal PCA.

Per- and polyfluoroalkyl substances (PFAS) are persistent environmental pollutants with known toxicity and bioaccumulation issues. Their widespread industrial use and resistance to degradation have led to global environmental contamination and significant health concerns. While a minority of PFAS have been extensively studied, the toxicity of many PFAS remains poorly understood due to limited direct toxicological data. This study advances the predictive modeling of PFAS toxicity by combining semi-supervised graph convolutional networks (GCNs) with molecular descriptors and fingerprints. We propose a novel approach to enhance the prediction of PFAS binding affinities by isolating molecular fingerprints to construct graphs where then descriptors are set as the node features. This approach specifically captures the structural, physicochemical, and topological features of PFAS without overfitting due to an abundance of features. Unsupervised clustering then identifies representative compounds for detailed binding studies. Our results provide a more accurate ability to estimate PFAS hepatotoxicity to provide guidance in chemical discovery of new PFAS and the development of new safety regulations.

Machine learning (ML) has been applied in many facets of chemistry, and its use is rapidly growing. We argue in this perspective that despite this dramatic growth and impact, ML could be employed better and more extensively. Current work is still far from exhausting the potential of ML to advance theory and application in chemistry in terms of breadth, depth, and scale. In addition, the actual types of problems that ML could tackle, such as hypothesis generation or enabling internalized scientific understanding, are still areas of active research or open problems.

In this paper, we provide tight lower bounds for the oracle complexity of minimizing high-order H\"older smooth and uniformly convex functions. Specifically, for a function whose $p^{th}$-order derivatives are H\"older continuous with degree $\nu$ and parameter $H$, and that is uniformly convex with degree $q$ and parameter $\sigma$, we focus on two asymmetric cases: (1) $q > p + \nu$, and (2) $q < p+\nu$. Given up to $p^{th}$-order oracle access, we establish worst-case oracle complexities of $\Omega\left( \left( \frac{H}{\sigma}\right)^\frac{2}{3(p+\nu)-2}\left( \frac{\sigma}{\epsilon}\right)^\frac{2(q-p-\nu)}{q(3(p+\nu)-2)}\right)$ with a truncated-Gaussian smoothed hard function in the first case and $\Omega\left(\left(\frac{H}{\sigma}\right)^\frac{2}{3(p+\nu)-2}+ \log^2\left(\frac{\sigma^{p+\nu}}{H^q}\right)^\frac{1}{p+\nu-q}\right)$ in the second case, for reaching an $\epsilon$-approximate solution in terms of the optimality gap. Our analysis generalizes previous lower bounds for functions under first- and second-order smoothness as well as those for uniformly convex functions, and furthermore our results match the corresponding upper bounds in the general setting.

Recent works for time-series forecasting more and more leverage the high predictive power of Deep Learning models. With this increase in model complexity, however, comes a lack in understanding of the underlying model decision process, which is problematic for high-stakes decision making. At the same time, simple, interpretable forecasting methods such as Linear Models can still perform very well, sometimes on-par, with Deep Learning approaches. We argue that simple models are good enough most of the time, and forecasting performance can be improved by choosing a Deep Learning method only for certain predictions, increasing the overall interpretability of the forecasting process. In this context, we propose a novel online model selection framework which uses meta-learning to identify these predictions and only rarely uses a non-interpretable, large model. An extensive empirical study on various real-world datasets shows that our selection methodology outperforms state-of-the-art online model selections methods in most cases. We find that almost always choosing a simple Linear Model for forecasting results in competitive performance, suggesting that the need for opaque black-box models in time-series forecasting is smaller than recent works would suggest.

Hypergraphs tackle the limitations of traditional graphs by introducing {\em hyperedges}. While graph edges connect only two nodes, hyperedges connect an arbitrary number of nodes along their edges. Also, the underlying message-passing mechanisms in Hypergraph Neural Networks (HGNNs) are in the form of vertex-hyperedge-vertex, which let HGNNs capture and utilize richer and more complex structural information than traditional Graph Neural Networks (GNNs). More recently, the idea of overlapping subgraphs has emerged. These subgraphs can capture more information about subgroups of vertices without limiting one vertex belonging to just one group, allowing vertices to belong to multiple groups or subgraphs. In addition, one of the most important problems in graph clustering is to find densest overlapping subgraphs (DOS). In this paper, we propose a solution to the DOS problem via Agglomerative Greedy Enumeration (DOSAGE) algorithm as a novel approach to enhance the process of generating the densest overlapping subgraphs and, hence, a robust construction of the hypergraphs. Experiments on standard benchmarks show that the DOSAGE algorithm significantly outperforms the HGNNs and six other methods on the node classification task.

Hunger crises are critical global issues affecting millions, particularly in low-income and developing countries. This research investigates how machine learning can be utilized to predict and inform decisions regarding famine and hunger crises. By leveraging a diverse set of variables (natural, economic, and conflict-related), three machine learning models (Linear Regression, XGBoost, and RandomForestRegressor) were employed to predict food consumption scores, a key indicator of household nutrition. The RandomForestRegressor emerged as the most accurate model, with an average prediction error of 10.6%, though accuracy varied significantly across countries, ranging from 2% to over 30%. Notably, economic indicators were consistently the most significant predictors of average household nutrition, while no single feature dominated across all regions, underscoring the necessity for comprehensive data collection and tailored, country-specific models. These findings highlight the potential of machine learning, particularly Random Forests, to enhance famine prediction, suggesting that continued research and improved data gathering are essential for more effective global hunger forecasting.