Statistical Learning
Neural Collapse To Multiple Centers For Imbalanced Data
NC phenomena occur with different loss functions.
Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning
This has motivated numerous studies aiming to reduce the variance and improve convergence of FL on non-IID data [6, 9, 14, 17, 19, 30]. On another note, constraints on communication resources and therefore on the number of clients that may participate in training additionally complicate implementation of FL schemes.
Conformal Meta-learners for Predictive Inference of Individual Treatment Effects
Previous work has focused primarily on developing ML-based "meta-learners" that can provide point estimates of the conditional
Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation Jiaming Lv, Haoyuan Y ang
Since pioneering work of Hinton et al., knowledge distillation based on Kullback-Leibler Divergence (KL-Div) has been predominant, and recently its variants have
Symmetry-InformedGoverningEquationDiscovery
Specifically, we derive equivariance constraints from the time-independent symmetries ofODEs.
A Notation Table
When the loss is set as squared loss, we can modify the functions regarding the truncated spectral projection.
No Change, No Gain: Empowering Graph Neural Networks with Expected Model Change Maximization for Active Learning
Graph Neural Networks (GNNs) are crucial for machine learning applications with graph-structured data, but their success depends on sufficient labeled data. We present a novel active learning (AL) method for GNNs, extending the Expected Model Change Maximization (EMCM) principle to improve prediction performance on unlabeled data. By presenting a Bayesian interpretation for the node embeddings generated by GNNs under the semi-supervised setting, we efficiently compute the closed-form EMCM acquisition function as the selection criterion for AL without re-training.