We study the complexity of learning real-valued Multi-Index Models (MIMs) under the Gaussian distribution. A $K$-MIM is a function $f:\mathbb{R}^d\to \mathbb{R}$ that depends only on the projection of its input onto a $K$-dimensional subspace. We give a general algorithm for PAC learning a broad class of MIMs with respect to the square loss, even in the presence of adversarial label noise. Moreover, we establish a nearly matching Statistical Query (SQ) lower bound, providing evidence that the complexity of our algorithm is qualitatively optimal as a function of the dimension. Specifically, we consider the class of bounded variation MIMs with the property that degree at most $m$ distinguishing moments exist with respect to projections onto any subspace. In the presence of adversarial label noise, the complexity of our learning algorithm is $d^{O(m)}2^{\mathrm{poly}(K/ε)}$. For the realizable and independent noise settings, our algorithm incurs complexity $d^{O(m)}2^{\mathrm{poly}(K)}(1/ε)^{O(K)}$. To complement our upper bound, we show that if for some subspace degree-$m$ distinguishing moments do not exist, then any SQ learner for the corresponding class of MIMs requires complexity $d^{Ω(m)}$. As an application, we give the first efficient learner for the class of positive-homogeneous $L$-Lipschitz $K$-MIMs. The resulting algorithm has complexity $\mathrm{poly}(d) 2^{\mathrm{poly}(KL/ε)}$. This gives a new PAC learning algorithm for Lipschitz homogeneous ReLU networks with complexity independent of the network size, removing the exponential dependence incurred in prior work.

Measuring task relatedness and mitigating negative transfer remain a critical open challenge in Multitask Learning (MTL). This work extends data attribution -- which quantifies the influence of individual training data points on model predictions -- to MTL setting for measuring task relatedness. We propose the MultiTask Influence Function (MTIF), a method that adapts influence functions to MTL models with hard or soft parameter sharing. Compared to conventional task relatedness measurements, MTIF provides a fine-grained, instance-level relatedness measure beyond the entire-task level. This fine-grained relatedness measure enables a data selection strategy to effectively mitigate negative transfer in MTL. Through extensive experiments, we demonstrate that the proposed MTIF efficiently and accurately approximates the performance of models trained on data subsets. Moreover, the data selection strategy enabled by MTIF consistently improves model performance in MTL. Our work establishes a novel connection between data attribution and MTL, offering an efficient and fine-grained solution for measuring task relatedness and enhancing MTL models.

Distribution shifts introduce uncertainty that undermines the robustness and generalization capabilities of machine learning models. While conventional wisdom suggests that learning causal-invariant representations enhances robustness to such shifts, recent empirical studies present a counterintuitive finding: (i) empirical risk minimization (ERM) can rival or even outperform state-of-the-art out-of-distribution (OOD) generalization methods, and (ii) its OOD generalization performance improves when all available covariates, not just causal ones, are utilized. Drawing on both empirical and theoretical evidence, we attribute this phenomenon to hidden confounding. Shifts in hidden confounding induce changes in data distributions that violate assumptions commonly made by existing OOD generalization approaches. Under such conditions, we prove that effective generalization requires learning environment-specific relationships, rather than relying solely on invariant ones. Furthermore, we show that models augmented with proxies for hidden confounders can mitigate the challenges posed by hidden confounding shifts. These findings offer new theoretical insights and practical guidance for designing robust OOD generalization algorithms and principled covariate selection strategies.

Evaluating multimodal large language models (MLLMs) is increasingly expensive, as the growing size and cross-modality complexity of benchmarks demand significant scoring efforts. To tackle with this difficulty, we introduce AutoJudger, an agent-driven framework for efficient and adaptive benchmarking of MLLMs that tackles this escalating cost. AutoJudger employs the Item Response Theory (IRT) to estimate the question difficulty and an autonomous evaluation agent to dynamically select the most informative test questions based on the model's real-time performance. Specifically, AutoJudger incorporates two pivotal components: a semantic-aware retrieval mechanism to ensure that selected questions cover diverse and challenging scenarios across both vision and language modalities, and a dynamic memory that maintains contextual statistics of previously evaluated questions to guide coherent and globally informed question selection throughout the evaluation process. Extensive experiments on four representative multimodal benchmarks demonstrate that our adaptive framework dramatically reduces evaluation expenses, i.e. AutoJudger uses only 4% of the data to achieve over 90% ranking accuracy with the full benchmark evaluation on MMT-Bench.

Despite rapid advances in large language models (LLMs), their integration with traditional supervised machine learning (ML) techniques that have proven applicability to medical data remains underexplored. This is particularly true for psychiatric applications, where narrative data often exhibit nuanced linguistic and contextual complexity, and can benefit from the combination of multiple models with differing characteristics. In this study, we introduce an ensemble framework for automatically classifying Attention-Deficit/Hyperactivity Disorder (ADHD) diagnosis (binary) using narrative transcripts. Our approach integrates three complementary models: LLaMA3, an open-source LLM that captures long-range semantic structure; RoBERTa, a pre-trained transformer model fine-tuned on labeled clinical narratives; and a Support Vector Machine (SVM) classifier trained using TF-IDF-based lexical features. These models are aggregated through a majority voting mechanism to enhance predictive robustness. The dataset includes 441 instances, including 352 for training and 89 for validation. Empirical results show that the ensemble outperforms individual models, achieving an F$_1$ score of 0.71 (95\% CI: [0.60-0.80]). Compared to the best-performing individual model (SVM), the ensemble improved recall while maintaining competitive precision. This indicates the strong sensitivity of the ensemble in identifying ADHD-related linguistic cues. These findings demonstrate the promise of hybrid architectures that leverage the semantic richness of LLMs alongside the interpretability and pattern recognition capabilities of traditional supervised ML, offering a new direction for robust and generalizable psychiatric text classification.

Graph Neural Networks (GNNs) have emerged as a powerful tool for processing data represented in graph structures, achieving remarkable success across a wide range of applications. However, to further improve the performance on graph classification benchmarks, structural representation of each node that encodes rich local topological information in the neighbourhood of nodes is an important type of feature that is often overlooked in the modeling. The consequence of neglecting the structural information has resulted high number of layers to connect messages from distant nodes which by itself produces other problems such as oversmoothing. In the present paper, we leverage these structural information that are modeled by anonymous random walks (ARWs) and introduce graph structure attention network (GSAT) which is a generalization of graph attention network(GAT) to integrate the original attribute and the structural representation to enforce the model to automatically find patterns for attending to different edges in the node neighbourhood to enrich graph representation. Our experiments show GSAT slightly improves SOTA on some graph classification benchmarks.

Department of Computer Science College of Engineering, Design and Physical Science Brunel University London steven.sam@brunel.ac.uk Abstract Agriculture constitut es a primary source of food production, economic growth and employment in India, but the sector is confronted with low farm productivity and yields aggravated by increased pressure on natural resources and adverse climate change variability. Efforts involv ing green revolution, land irrigations, improved seeds and organic farming have yielded suboptimal outcomes. The adoption of innovative computational solutions such as crop recommendation systems is considered as a new frontier to provide insights and help farmers adapt and address the challenge of low productivity. However, existing agricultural recommendation systems have predominantly focused on environmental factors and narrow geographical coverage in India, resulting in limited and robust predictions o f suitable crops with both maximum yields and profits. This work incorporates both environmental and economic factors and 19 crop varieties across 15 states as input parameters to develop and evaluate two recommendation module s - Random Forest (RF) and Support Vector Machines (SVM) - using 10 - fold Cross Validation, Time - series Split and Lag Variables approaches. Results show that the 10 - fold cross validation approach produced exceptionally high accuracy (RF: 99.96%, SVM: 94.71%), raising concerns of overfitting. However, the introduction of temporal order, which aligns more with real - world scenarios, reduces the model performance (RF: 78.55%, SVM: 71.18%) in the Time - series Split approach. To further increase the model accuracy while maintaining the temporal order, the Lag Variables approach was employed, which resulted in improved performance (RF: 83.62%, SVM: 74.38%) compared to the 10 - fold cross validation approach. Consequently, the study shows the Random Forest model developed based on the Lag Variables as the most preferred algorithm for op timal crop recommendation in the Indian context. Key words: Crop recommendation model; Random forest; Support vector machines; Indian agriculture; Exploratory data analysis 1. Introduction Agriculture is not only fundamental for food production but also constitutes a primary source for economic growth, employment and improvement of the wellbeing of many people globally. For example, the World Bank reports that agriculture constitutes about 4 % of the world's total gross domestic product (GDP), and in certain least developed nations, its contribution to GDP exceeds 25%.

Citations play a fundamental role in the scientific ecosystem, serving as a foundation for tracking the flow of knowledge, acknowledging prior work, and assessing scholarly influence. In scientometrics, they are also central to the construction of quantitative indicators. Not all citations, however, serve the same function: some provide background, others introduce methods, or compare results. Therefore, understanding citation intent allows for a more nuanced interpretation of scientific impact. In this paper, we adopted a GAN-based method to classify citation intents. Our results revealed that the proposed method achieves competitive classification performance, closely matching state-of-the-art results with substantially fewer parameters. This demonstrates the effectiveness and efficiency of leveraging GAN architectures combined with contextual embeddings in intent classification task. We also investigated whether filtering citation intents affects the centrality of papers in citation networks. Analyzing the network constructed from the unArXiv dataset, we found that paper rankings can be significantly influenced by citation intent. All four centrality metrics examined- degree, PageRank, closeness, and betweenness - were sensitive to the filtering of citation types. The betweenness centrality displayed the greatest sensitivity, showing substantial changes in ranking when specific citation intents were removed.

The growing need for synthetic time series, due to data augmentation or privacy regulations, has led to numerous generative models, frameworks, and evaluation measures alike. Objectively comparing these measures on a large scale remains an open challenge. We propose the Synthetic Time series Evaluation Benchmark (STEB) -- the first benchmark framework that enables comprehensive and interpretable automated comparisons of synthetic time series evaluation measures. Using 10 diverse datasets, randomness injection, and 13 configurable data transformations, STEB computes indicators for measure reliability and score consistency. It tracks running time, test errors, and features sequential and parallel modes of operation. In our experiments, we determine a ranking of 41 measures from literature and confirm that the choice of upstream time series embedding heavily impacts the final score.

Conformal prediction (CP) is a powerful framework for uncertainty quantification, providing prediction sets with coverage guarantees when calibrated on sufficient labeled data. However, in real-world applications where labeled data is often limited, standard CP can lead to coverage deviation and output overly large prediction sets. In this paper, we extend CP to the semi-supervised setting and propose SemiCP, leveraging both labeled data and unlabeled data for calibration. Specifically, we introduce a novel nonconformity score function, NNM, designed for unlabeled data. This function selects labeled data with similar pseudo-label scores to estimate nonconformity scores, integrating them into the calibration process to overcome sample size limitations. We theoretically demonstrate that, under mild assumptions, SemiCP provide asymptotically coverage guarantee for prediction sets. Extensive experiments further validate that our approach effectively reduces instability and inefficiency under limited calibration data, can be adapted to conditional coverage settings, and integrates seamlessly with existing CP methods.