Related papers: Manifold-Aligned Guided Integrated Gradients for R…

Representing graph data in a low-dimensional space for subsequent tasks is the purpose of attributed graph embedding. Most existing neural network approaches learn latent representations by minimizing reconstruction errors. Rare work…

Interpretation and improvement of deep neural networks relies on better understanding of their underlying mechanisms. In particular, gradients of classes or concepts with respect to the input features (e.g., pixels in images) are often used…

The last decade has witnessed the success of deep learning and the surge of publicly released trained models, which necessitates the quantification of the model functional distance for various purposes. However, quantifying the model…

Generating executable CAD programs from images requires alignment between visual geometry and symbolic program representations, a capability that current methods fail to learn reliably as design complexity increases. Existing fine-tuning…

Federated Learning (FL) enables privacy-preserving multi-source information fusion (MSIF) but is challenged by client drift in highly heterogeneous data settings. Many existing drift-mitigation strategies rely on reference-based…

Attribution methods calculate attributions that visually explain the predictions of deep neural networks (DNNs) by highlighting important parts of the input features. In particular, gradient-based attribution (GBA) methods are widely used…

Feature attributions are post-training analysis methods that assess how various input features of a machine learning model contribute to an output prediction. Their interpretation is straightforward when features act independently, but it…

Feature distillation is an effective way to improve the performance for a smaller student model, which has fewer parameters and lower computation cost compared to the larger teacher model. Unfortunately, there is a common obstacle - the gap…

Unified image restoration using a single model often faces task interference due to diverse degradations. To address this, we propose DACG-IR (Degradation-Aware Adaptive Context Gating), which enables explicit perception of degradation…

Gradient Smoothing is an efficient approach to reducing noise in gradient-based model explanation method. SmoothGrad adds Gaussian noise to mitigate much of these noise. However, the crucial hyper-parameter in this method, the variance…

Multifidelity models integrate data from multiple sources to produce a single approximator for the underlying process. Dense low-fidelity samples are used to reduce interpolation error, while sparse high-fidelity samples are used to…

Generative recommendation (GR) with semantic IDs (SIDs) has emerged as a promising alternative to traditional recommendation approaches due to its performance gains, capitalization on semantic information provided through language model…

Rich feature representations derived from CLIP-ViT have been widely utilized in AI-generated image detection. While most existing methods primarily leverage features from the final layer, we systematically analyze the contributions of…

Automated radiology report generation has gained increasing attention with the rise of deep learning and large language models. However, fully generative approaches often suffer from hallucinations and lack clinical grounding, limiting…

Scene Graph Generation (SGG) suffers from a long-tailed distribution, where a few predicate classes dominate while many others are underrepresented, leading to biased models that underperform on rare relations. Unbiased-SGG methods address…

We present a novel graph-based learning of EEG representations with gradient alignment (GEEGA) that leverages multi-domain information to learn EEG representations for brain-computer interfaces. Our model leverages graph convolutional…

Safe manipulation-oriented navigation for humanoid robots requires scene memory that remains reliable under locomotion-induced perceptual distortion, environmental changes, and interaction-level geometric safety constraints. Existing…

Intrinsic image decomposition (IID) is an under-constrained problem. Therefore, traditional approaches use hand crafted priors to constrain the problem. However, these constraints are limited when coping with complex scenes. Deep…

Recent years have seen substantial progress in neural generation of text, images, and audio, supported by mature training pipelines and large-scale optimization. For graphs, however, comparable progress has been more limited. We attribute…

Despite the recent advancements, conditional image generation still faces challenges of cost, generalizability, and the need for task-specific training. In this paper, we propose Manifold Preserving Guided Diffusion (MPGD), a training-free…