Zobrazeno 1 - 10
of 52
pro vyhledávání: '"Han, Andi"'
Graph Neural Networks (GNNs) are proficient in graph representation learning and achieve promising performance on versatile tasks such as node classification and link prediction. Usually, a comprehensive hyperparameter tuning is essential for fully u
Externí odkaz:
http://arxiv.org/abs/2410.05697
The Adam optimizer is widely used for transformer optimization in practice, which makes understanding the underlying optimization mechanisms an important problem. However, due to the Adam's complexity, theoretical analysis of how it optimizes transfo
Externí odkaz:
http://arxiv.org/abs/2410.04870
Graph Neural Networks (GNNs) have emerged as fundamental tools for a wide range of prediction tasks on graph-structured data. Recent studies have drawn analogies between GNN feature propagation and diffusion processes, which can be interpreted as dyn
Externí odkaz:
http://arxiv.org/abs/2410.05593
The advent of deep learning has introduced efficient approaches for de novo protein sequence design, significantly improving success rates and reducing development costs compared to computational or experimental methods. However, existing methods fac
Externí odkaz:
http://arxiv.org/abs/2407.07443
Many machine learning applications are naturally formulated as optimization problems on Riemannian manifolds. The main idea behind Riemannian optimization is to maintain the feasibility of the variables while moving along a descent direction on the m
Externí odkaz:
http://arxiv.org/abs/2406.02225
Autor:
Han, Andi, Li, Jiaxiang, Huang, Wei, Hong, Mingyi, Takeda, Akiko, Jawanpuria, Pratik, Mishra, Bamdev
Large language models (LLMs) have shown impressive capabilities across various tasks. However, training LLMs from scratch requires significant computational power and extensive memory capacity. Recent studies have explored low-rank structures on weig
Externí odkaz:
http://arxiv.org/abs/2406.02214
Graph Neural Networks (GNNs) are deep-learning architectures designed for graph-type data, where understanding relationships among individual observations is crucial. However, achieving promising GNN performance, especially on unseen data, requires c
Externí odkaz:
http://arxiv.org/abs/2405.12521
Bilevel optimization has seen an increasing presence in various domains of applications. In this work, we propose a framework for solving bilevel optimization problems where variables of both lower and upper level problems are constrained on Riemanni
Externí odkaz:
http://arxiv.org/abs/2402.03883
Physics-informed Graph Neural Networks have achieved remarkable performance in learning through graph-structured data by mitigating common GNN challenges such as over-smoothing, over-squashing, and heterophily adaption. Despite these advancements, th
Externí odkaz:
http://arxiv.org/abs/2401.14580
Traffic forecasting, a crucial application of spatio-temporal graph (STG) learning, has traditionally relied on deterministic models for accurate point estimations. Yet, these models fall short of quantifying future uncertainties. Recently, many prob
Externí odkaz:
http://arxiv.org/abs/2401.08119