Graph Transformers (GTs) have demonstrated great effectiveness across various graph analytical tasks. However, the existing GTs focus on training and testing graph data originated from the same distribution, but fail to generalize under distribution shifts. Graph invariant learning, aiming to capture generalizable graph structural patterns with labels under distribution shifts, is potentially a promising solution, but how to design attention mechanisms and positional and structural encodings (PSEs) based on graph invariant learning principles remains challenging. To solve these challenges, we introduce Graph Out-Of-Distribution generalized Transformer (GOODFormer), aiming to learn generalized graph representations by capturing invariant relationships between predictive graph structures and labels through jointly optimizing three modules. Specifically, we first develop a GT-based entropy-guided invariant subgraph disentangler to separate invariant and variant subgraphs while preserving the sharpness of the attention function. Next, we design an evolving subgraph positional and structural encoder to effectively and efficiently capture the encoding information of dynamically changing subgraphs during training. Finally, we propose an invariant learning module utilizing subgraph node representations and encodings to derive generalizable graph representations that can to unseen graphs. We also provide theoretical justifications for our method. Extensive experiments on benchmark datasets demonstrate the superiority of our method over state-of-the-art baselines under distribution shifts.

We present an online tutoring system that learns to provide effective feedback to students after they answer questions incorrectly. Using data from one million students, the system learns which assistance action (e.g., one of multiple hints) to provide for each question to optimize student learning. Employing the multi-armed bandit (MAB) framework and offline policy evaluation, we assess 43,000 assistance actions, and identify trade-offs between assistance policies optimized for different student outcomes (e.g., response correctness, session completion). We design an algorithm that for each question decides on a suitable policy training objective to enhance students' immediate second attempt success and overall practice session performance. We evaluate the resulting MAB policies in 166,000 practice sessions, verifying significant improvements in student outcomes. While MAB policies optimize feedback for the overall student population, we further investigate whether contextual bandit (CB) policies can enhance outcomes by personalizing feedback based on individual student features (e.g., ability estimates, response times). Using causal inference, we examine (i) how effects of assistance actions vary across students and (ii) whether CB policies, which leverage such effect heterogeneity, outperform MAB policies. While our analysis reveals that some actions for some questions exhibit effect heterogeneity, effect sizes may often be too small for CB policies to provide significant improvements beyond what well-optimized MAB policies that deliver the same action to all students already achieve. We discuss insights gained from deploying data-driven systems at scale and implications for future refinements. Today, the teaching policies optimized by our system support thousands of students daily.

Foundation models (FMs) pretrained on large datasets have become fundamental for various downstream machine learning tasks, in particular in scenarios where obtaining perfectly labeled data is prohibitively expensive. In this paper, we assume an FM has to be fine-tuned with noisy data and present a two-stage framework to ensure robust classification in the presence of label noise without model retraining. Recent work has shown that simple k-nearest neighbor (kNN) approaches using an embedding derived from an FM can achieve good performance even in the presence of severe label noise. Our work is motivated by the fact that these methods make use of local geometry. In this paper, following a similar two-stage procedure, reliability estimation followed by reliability-weighted inference, we show that improved performance can be achieved by introducing geometry information. For a given instance, our proposed inference uses a local neighborhood of training data, obtained using the non-negative kernel (NNK) neighborhood construction. We propose several methods for reliability estimation that can rely less on distance and local neighborhood as the label noise increases. Our evaluation on CIFAR-10 and DermaMNIST shows that our methods improve robustness across various noise conditions, surpassing standard K-NN approaches and recent adaptive-neighborhood baselines.

Standard regression techniques, while powerful, are often constrained by predefined, differentiable loss functions such as mean squared error. These functions may not fully capture the desired behavior of a system, especially when dealing with asymmetric costs or complex, non-differentiable objectives. In this paper, we explore an alternative paradigm: framing regression as a Reinforcement Learning (RL) problem. We demonstrate this by treating a model's prediction as an action and defining a custom reward signal based on the prediction error, and we can leverage powerful RL algorithms to perform function approximation. Through a progressive case study of learning a noisy sine wave, we illustrate the development of an Actor-Critic agent, iteratively enhancing it with Prioritized Experience Replay, increased network capacity, and positional encoding to enable a capable RL agent for this regression task. Our results show that the RL framework not only successfully solves the regression problem but also offers enhanced flexibility in defining objectives and guiding the learning process.

We propose a new deflation strategy to accelerate the convergence of the preconditioned conjugate gradient(PCG) method for solving parametric large-scale linear systems of equations. Unlike traditional deflation techniques that rely on eigenvector approximations or recycled Krylov subspaces, we generate the deflation subspaces using operator learning, specifically the Deep Operator Network~(DeepONet). To this aim, we introduce two complementary approaches for assembling the deflation operators. The first approach approximates near-null space vectors of the discrete PDE operator using the basis functions learned by the DeepONet. The second approach directly leverages solutions predicted by the DeepONet. To further enhance convergence, we also propose several strategies for prescribing the sparsity pattern of the deflation operator. A comprehensive set of numerical experiments encompassing steady-state, time-dependent, scalar, and vector-valued problems posed on both structured and unstructured geometries is presented and demonstrates the effectiveness of the proposed DeepONet-based deflated PCG method, as well as its generalization across a wide range of model parameters and problem resolutions.

This paper introduces Stress-Aware Learning, a resilient neural training paradigm in which deep neural networks dynamically adjust their optimization behavior - whether under stable training regimes or in settings with uncertain dynamics - based on the concept of Temporary (Elastic) and Permanent (Plastic) Deformation, inspired by structural fatigue in materials science. To instantiate this concept, we propose Plastic Deformation Optimizer, a stress-aware mechanism that injects adaptive noise into model parameters whenever an internal stress signal - reflecting stagnation in training loss and accuracy - indicates persistent optimization difficulty. This enables the model to escape sharp minima and converge toward flatter, more generalizable regions of the loss landscape. Experiments across six architectures, four optimizers, and seven vision benchmarks demonstrate improved robustness and generalization with minimal computational overhead. The code and 3D visuals will be available on GitHub: https://github.com/Stress-Aware-Learning/SAL.

This study proposes a novel methodological framework integrating a LightGBM regression model and genetic algorithm (GA) optimization to systematically evaluate the contribution of COVID - 19 - related indicators to Bitcoin return prediction. The primary object ive was not merely to forecast Bitcoin returns but rather to determine whether including pandemic - related health data significantly enhances prediction accuracy. A comprehensive dataset comprising daily Bitcoin returns and COVID - 19 metrics (vaccination rat es, hospitalizations, testing statistics) was constructed. Predictive models, trained with and without COVID - 19 features, were optimized using GA over 31 independent runs, allowing robust statistical assessment. Performance metrics (R, RMSE, MAE) were sta tistically compared through distribution overlaps and Mann - Whitney U tests. Permutation Feature Importance (PFI) analysis quantified individual feature contributions. Results indicate that COVID - 19 indicators significantly improved model performance, parti cularly in capturing extreme market fluctuations (R increased by 40%, RMSE decreased by 2%, both highly significant statistically). Among COVID - 19 features, vaccination metrics, especially the 75th percentile of fully vaccinated individuals, emerged as dominant predictors. The proposed methodology extends existing financial analytics tools by incorporating public health signals, providing investors and policymakers with refined indicators to navigate market uncertainty during systemic crises.

First and second authors contributed equally to this work Abstract --Modern recommenders describe each item with hundreds of sparse semantic tags, yet most quantum pipelines still map one qubit per tag, demanding well beyond one hundred qubits, far out of reach for current noisy-intermediate-scale quantum (NISQ) devices and prone to deep, error-amplifying circuits. We close this gap with a three-stage hybrid machine learning algorithm that compresses tag profiles, optimizes feature selection under a fixed qubit budget via QAOA, and scores recommendations with a Quantum semi-Random Forest (QsRF) built on just five qubits, while performing similarly to the state-of-the-art methods. Leveraging SVD sketching and k-means, we learn a 1 000-atom dictionary ( >97 % variance), then solve a 20 20 QUBO via depth-3 QAOA to select 5 atoms. A 100-tree QsRF trained on these codes matches full-feature baselines on ICM-150/500. To compress this combinatorial explosion, recent hybrid pipelines formulate feature selection as a Q uadratic U nconstrained Binary O ptimisation (QUBO) and delegate the search to quantum annealers [1], [2] or shallow gate-based circuits [3].

Data quality plays a pivotal role in the predictive performance of machine learning (ML) tasks - a challenge amplified by the deluge of data sources available in modern organizations. Prior work in data discovery largely focus on metadata matching, semantic similarity or identifying tables that should be joined to answer a particular query, but do not consider source quality for high performance of the downstream ML task. This paper addresses the problem of determining the best subset of data sources that must be combined to construct the underlying training dataset for a given ML task. We propose SourceGrasp and SourceSplice, frameworks designed to efficiently select a suitable subset of sources that maximizes the utility of the downstream ML model. Both the algorithms rely on the core idea that sources (or their combinations) contribute differently to the task utility, and must be judiciously chosen. While SourceGrasp utilizes a metaheuristic based on a greediness criterion and randomization, the SourceSplice framework presents a source selection mechanism inspired from gene splicing - a core concept used in protein synthesis. We empirically evaluate our algorithms on three real-world datasets and synthetic datasets and show that, with significantly fewer subset explorations, SourceSplice effectively identifies subsets of data sources leading to high task utility. We also conduct studies reporting the sensitivity of SourceSplice to the decision choices under several settings.

Neoclassical economics identifies preferences with choice s. That Alice prefers x to y means only that Alice chooses x when presented with the binary-choice problem "would you li ke x or y?" As a consequence of this view, and given the great availabi lity of choice data from various sources, economists have developed and used an extensi ve methodology for analyzing choice data. Choice data are used in estimating preferences, in predicting agents' behavior out of sample, and in conducting counterfactual analysis. Ther e is, however, a growing acceptance in the profession that preferences could be meaningful beyo nd their interpretation as choices. Many economists now think that non-choice data have a role to play in the estimation of preferences and the prediction of agents' behavior. Now, while t here is substantial interest in the use of non-choice data, there is not yet a mature statistical methodological body of work designed for working with economic non-choice data. Our paper presents progress towards such a methodology . W e develop empirical methodology to estimate preferences f rom choice and response-time data.