Zobrazeno 1 - 10
of 71
pro vyhledávání: '"Heimann, Mark"'
While graph neural networks (GNNs) are widely used for node and graph representation learning tasks, the reliability of GNN uncertainty estimates under distribution shifts remains relatively under-explored. Indeed, while post-hoc calibration strategi
Externí odkaz:
http://arxiv.org/abs/2401.03350
Safe deployment of graph neural networks (GNNs) under distribution shift requires models to provide accurate confidence indicators (CI). However, while it is well-known in computer vision that CI quality diminishes under distribution shift, this beha
Externí odkaz:
http://arxiv.org/abs/2309.10976
Autor:
Loveland, Donald, Zhu, Jiong, Heimann, Mark, Fish, Benjamin, Schaub, Michael T., Koutra, Danai
Graph Neural Network (GNN) research has highlighted a relationship between high homophily (i.e., the tendency of nodes of the same class to connect) and strong predictive performance in node classification. However, recent work has found the relation
Externí odkaz:
http://arxiv.org/abs/2306.05557
Network alignment, or the task of finding corresponding nodes in different networks, is an important problem formulation in many application domains. We propose CAPER, a multilevel alignment framework that Coarsens the input graphs, Aligns the coarse
Externí odkaz:
http://arxiv.org/abs/2208.10682
Recent analyses of self-supervised learning (SSL) find the following data-centric properties to be critical for learning good representations: invariance to task-irrelevant semantics, separability of classes in some latent space, and recoverability o
Externí odkaz:
http://arxiv.org/abs/2208.02810
Autor:
Subramanyam, Rakshith, Heimann, Mark, Thathachar, Jayram, Anirudh, Rushil, Thiagarajan, Jayaraman J.
Model agnostic meta-learning algorithms aim to infer priors from several observed tasks that can then be used to adapt to a new task with few examples. Given the inherent diversity of tasks arising in existing benchmarks, recent methods use separate,
Externí odkaz:
http://arxiv.org/abs/2207.12346
We study the task of node classification for graph neural networks (GNNs) and establish a connection between group fairness, as measured by statistical parity and equal opportunity, and local assortativity, i.e., the tendency of linked nodes to have
Externí odkaz:
http://arxiv.org/abs/2207.04376
Autor:
Georgouli, Konstantia, Ingólfsson, Helgi I, Aydin, Fikret, Heimann, Mark, Lightstone, Felice C, Bremer, Peer-Timo, Bhatia, Harsh
Capturing intricate biological phenomena often requires multiscale modeling where coarse and inexpensive models are developed using limited components of expensive and high-fidelity models. Here, we consider such a multiscale framework in the context
Externí odkaz:
http://arxiv.org/abs/2207.04333
Autor:
Liskov, Steven, Olleik, Farah, Jarrett, Harish, Abramson, Sandra, Kowey, Peter, Schaller, Robert D., Vijayaraman, Pugazhendi, Habibi, Mohammadali, Bansal, Shefali, Heimann, Mark, Cox, Scott, Keramati, Ali R.
Publikováno v:
In CJC Open September 2024 6(9):1058-1065
While most network embedding techniques model the relative positions of nodes in a network, recently there has been significant interest in structural embeddings that model node role equivalences, irrespective of their distances to any specific nodes
Externí odkaz:
http://arxiv.org/abs/2102.13582