影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
87.27/100
前 0.8%
全站排名 #499
发表论文23 篇
平均评分
年均产出7.7 篇/年
Rebekka Burkholz
研究方向
deep learning efficiency · deep learning · theory · deep information propagation · message passing · GNNs · social network analysis · cascades
21
When Shift Happens - Confounding Is to Blame
ICLR 2026Poster
三作23
Hyperbolic Aware Minimization: Implicit Bias for Sparsity
ICLR 2026Poster
通讯27
Fixed Aggregation Features Can Rival GNNs
ICLR 2026Rejected
二作20
Boosting for Predictive Sufficiency
ICLR 2026Poster
通讯23
Never Saddle for Reparameterized Steepest Descent as Mirror Flow
ICLR 2026Poster
三作7
Unmasking the Success of Mixture of Experts: Noisy Features, Sparse Experts
ICLR 2026Withdrawn
三作4
Random Features for Normalization Layers
ICLR 2026Withdrawn
一作21
The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis
NeurIPS 2025Spotlight
20
Pay Attention to Small Weights
NeurIPS 2025Poster
通讯28
Sign-In to the Lottery: Reparameterizing Sparse Training
NeurIPS 2025Poster
通讯17
Mask in the Mirror: Implicit Sparsification
ICLR 2025Poster
二作7
Mirror, Mirror of the Flow: How Does Regularization Shape Implicit Bias?
ICML 2025Poster
三作33
GNNs Getting ComFy: Community and Feature Similarity Guided Rewiring
ICLR 2025Poster
三作10
Memory Savings by Sharing One Source: Insights into Subsetsum Approximation
ICLR 2025Withdrawn
三作6
SoLAR: Surrogate Label Aware GNN Rewiring
ICLR 2025Withdrawn
三作16
Time-Dependent Mirror Flows and Where to Find Them
ICLR 2025Rejected
三作5
PaI is getting competitive by training longer
ICLR 2025Withdrawn
三作