Deep Learning

GSIP framework mitigates catastrophic forgetting in graph class incremental learning by preserving crucial graph information, achieving a 10% improvement in forgetting metrics.

Quantum-physics-aware neural networks achieve up to 50% improved accuracy in predicting quantum computer capabilities, scaling to 100+ qubits.

Boost OOD detection accuracy by averaging model confidence scores from original and corrupted inputs!

WeiPer enhances OOD detection by cleverly perturbing class projections, creating a richer representation that improves various existing methods and achieves state-of-the-art results.

Optimal fault-tolerant asynchronous machine learning is achieved via a novel weighted robust aggregation framework, ensuring efficient training despite Byzantine failures and heterogeneous resources.

Weight Diffusion (W-Diff) masters evolving domain generalization by using conditional diffusion models to learn classifier weight evolution patterns, enabling superior generalization to unseen future …

Weight decay in deep learning surprisingly induces low-rank attention layers, potentially harming performance but offering optimization strategies for large language models.

WaveAttack: A new backdoor attack method leveraging asymmetric frequency obfuscation for high stealthiness and effectiveness in Deep Neural Networks.

Wasserstein Gradient Boosting (WGBoost) extends gradient boosting to handle probability distributions as outputs, enabling more robust and informative predictions in various applications.

CatFlow: a novel flow matching method for graph generation, offering superior computational efficiency and performance.

ImagenTime transforms time series into images, leveraging advanced diffusion models for superior generative modeling of both short and long sequences.

Neural network efficiency is improved by analyzing weight norm variance across channels to identify optimal layer widths, resulting in reduced parameters and boosted performance.

Universal Physics Transformers (UPTs) offer a unified, scalable framework for efficiently training neural operators across diverse spatio-temporal physics problems, overcoming limitations of existing …

Universal Neural Functionals (UNFs) automatically construct permutation-equivariant models for any weight space, improving learned optimizer performance and generalization.

UniTS: one model to rule them all! This unified multi-task time series model excels in forecasting, classification, anomaly detection, and imputation, outperforming specialized models across 38 divers…

ADV-TRA uses adversarial trajectories to robustly fingerprint deep neural networks, outperforming state-of-the-art methods against various removal attacks.

UniIF: A unified model revolutionizes molecule inverse folding, achieving state-of-the-art results across protein, RNA, and material design by employing a novel geometric block attention network.

TFE-GNN: A novel spectral GNN using triple filter ensembles for superior homophily/heterophily handling and improved generalization on real-world graphs.

Latent Graph Diffusion (LGD) unifies graph learning, solving all task levels and types with a single framework and state-of-the-art results.

A mean-field theory explains Fourier Neural Operator (FNO) behavior, linking expressivity to trainability by identifying ordered and chaotic phases that correspond to vanishing or exploding gradients,…