12566 papers
This paper introduces the Wasserstein Transform, a general unsupervised framework that enhances features and denoises data by representing points as probability measures and updating distances via Wasserstein metrics, with a specific focus on the computationally efficient Gaussian Transform variant and its applications in tasks like clustering and image segmentation.
This paper introduces AXIL, an exact, efficient, and scalable instance-attribution method for gradient boosting machines that computes prediction-specific weights via a matrix-free backward operator, outperforming existing methods in both faithfulness tests and computational speed while unifying exact decomposition with broader implicit differentiation frameworks.
This paper proposes a novel "agnostic inference attack" in vertical federated learning where an active party infers passive party features using an independently trained model, and introduces adjustable privacy-preserving schemes that distort passive parameters to mitigate this attack while balancing privacy and model interpretability.
The paper proposes SIGMA, an efficient heterophilous graph neural network that leverages SimRank-based global aggregation to achieve state-of-the-art performance with linear time complexity, overcoming the efficiency limitations of existing iterative methods on large-scale graphs.
This paper addresses the challenge of incentivizing honesty among competing participants in collaborative learning by formulating a game-theoretic framework that identifies rational incentives for manipulation and proposes mechanisms to ensure high-quality learning outcomes comparable to full cooperation.
The paper introduces SciTune, a framework that aligns large language models with human-curated scientific multimodal instructions, resulting in a model (LLaMA-SciTune) that significantly outperforms state-of-the-art systems on scientific visual and language benchmarks, even surpassing human performance in certain categories.
This paper proposes PePNet, a workload prediction network that adaptively fuses changeable periodicity information and employs an Achilles' Heel Loss Function to significantly improve prediction accuracy for rare heavy workloads in cloud servers, thereby reducing Service Level Agreement violations.
The paper introduces MM-LIMA, a multimodal large language model that achieves superior performance compared to MiniGPT-4 by utilizing a trainable data selector to filter and fine-tune on a small, high-quality dataset of just 200 examples, demonstrating that less but higher-quality instruction data is more effective for alignment.
This paper proposes CROP, a model-based offline reinforcement learning algorithm that introduces a conservative reward estimator to mitigate distribution shift and overestimation by minimizing both estimation error and the rewards of random actions, achieving competitive performance through a streamlined objective.
This paper proposes a novel statistical benchmarking strategy that tests for treatment effect bias in specific subgroups by comparing observational study estimates against randomized trials, ultimately providing an asymptotically valid lower bound on maximum bias strength to ensure reliable clinical decision-making.
This paper introduces a generalized debiased Lasso estimator that leverages a stability principle to provide a computationally efficient, asymptotically accurate update formula for perturbed designs, thereby significantly reducing the cost of resampling-based variable selection methods like the conditional randomization test and local knockoff filter.
This paper proposes a training-free, multi-user generative semantic communication framework that leverages null-space diffusion sampling to transmit only essential bits for receivers to regenerate missing information, thereby optimizing OFDMA systems for next-generation GenAI-based communications.
This paper proposes a practical continuous-time reinforcement learning framework for intensity control in choice-based network revenue management that leverages event-driven structures to avoid time discretization, demonstrating superior performance and scalability compared to state-of-the-art discretization-based methods.
This paper proposes ITEM, an iterative framework inspired by Schutz's philosophical system of relevances that enhances the retrieval, utility judgment, and answer generation stages of Retrieval-Augmented Generation (RAG) systems, demonstrating significant improvements across multiple datasets.
LaMI proposes a late multi-image fusion method that augments text-only Large Language Models with test-time visual signals generated via parallel sampling, significantly improving visual commonsense reasoning and NLP performance without the high costs of full multimodal training or the degradation of textual capabilities.
This paper proposes a sample-efficient offline reinforcement learning approach for fixed-wing aircraft lateral attitude tracking that leverages system symmetry to augment training data and employs a dual-critic Deep Deterministic Policy Gradient (DDPG) structure to accelerate policy convergence.
This paper addresses the unexplored robustness of Graph Transformers by designing the first adaptive gradient-based attacks against various architectures, revealing their catastrophic fragility to structural perturbations and demonstrating how these attacks can be leveraged to significantly improve their robustness through adversarial training.
This paper introduces "Poisoning with A Pill," a three-stage augmentation framework that enhances the stealth and effectiveness of federated learning poisoning attacks by strategically injecting malicious updates into a tiny, novel subnet structure, thereby bypassing existing detection defenses and significantly increasing model error rates across diverse FL scenarios.
FedQUIT is a novel on-device federated unlearning algorithm that leverages a quasi-competent virtual teacher-student framework to effectively remove client data contributions from a global model without requiring additional assumptions beyond standard FedAvg, while significantly reducing communication and computational overhead compared to retraining.
This paper proposes a novel, fast-converging greedy algorithm that accurately identifies the optimal number and locations of breakpoints in piecewise polynomial regression, demonstrating superior accuracy and interpretability over existing methods on both synthetic and real-world datasets.