970 citations · 3k across the 88 of their papers we have counts for
12 papers · 1 filter
Counting Substructures with Higher-Order Graph Neural Networks: Possibility and Impossibility Results
Behrooz Tahmasebi, Derek Lim, Stefanie Jegelka
While message passing Graph Neural Networks (GNNs) have become increasingly popular architectures for learning with graphs, recent works have revealed important shortcomings in the…
Contrastive Learning with Hard Negative Samples
Joshua Robinson, Ching-Yao Chuang, Suvrit Sra +1
How can you sample good negative examples for contrastive learning? We argue that, as with metric learning, contrastive learning of representations benefits from hard negative samp…
Information Obfuscation of Graph Neural Networks
Peiyuan Liao, Han Zhao, Keyulu Xu +4
While the advent of Graph Neural Networks (GNNs) has greatly improved node and graph representation learning in many applications, the neighborhood aggregation scheme exposes addit…
How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks
Keyulu Xu, Mozhi Zhang, Jingling Li +3
We study how neural networks trained by gradient descent extrapolate, i.e., what they learn outside the support of the training distribution. Previous works report mixed empirical…
Testing Determinantal Point Processes
Khashayar Gatmiry, Maryam Aliakbarpour, Stefanie Jegelka
Determinantal point processes (DPPs) are popular probabilistic models of diversity. In this paper, we investigate DPPs from a new perspective: property testing of distributions. Gi…
Estimating Generalization under Distribution Shifts via Domain-Invariant Representations
Ching-Yao Chuang, Antonio Torralba, Stefanie Jegelka
When machine learning models are deployed on a test distribution different from the training distribution, they can perform poorly, but overestimate their performance. In this work…
Debiased Contrastive Learning
Ching-Yao Chuang, Joshua Robinson, Lin Yen-Chen +2
A prominent technique for self-supervised representation learning has been to contrast semantically similar and dissimilar pairs of samples. Without access to labels, dissimilar (n…
IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method
Yossi Arjevani, Joan Bruna, Bugra Can +3
We introduce a framework for designing primal methods under the decentralized optimization setting where local functions are smooth and strongly convex. Our approach consists of ap…
Distributionally Robust Bayesian Optimization
Johannes Kirschner, Ilija Bogunovic, Stefanie Jegelka +1
Robustness to distributional shift is one of the key challenges of contemporary machine learning. Attaining such robustness is the goal of distributionally robust optimization, whi…
Strength from Weakness: Fast Learning Using Weak Supervision
Joshua Robinson, Stefanie Jegelka, Suvrit Sra
We study generalization properties of weakly supervised learning. That is, learning where only a few "strong" labels (the actual target of our prediction) are present but many more…
Generalization and Representational Limits of Graph Neural Networks
Vikas K. Garg, Stefanie Jegelka, Tommi Jaakkola
We address two fundamental questions about graph neural networks (GNNs). First, we prove that several important graph properties cannot be computed by GNNs that rely entirely on lo…
On the Complexity of Minimizing Convex Finite Sums Without Using the Indices of the Individual Functions
Yossi Arjevani, Amit Daniely, Stefanie Jegelka +1
Recent advances in randomized incremental methods for minimizing -smooth -strongly convex finite sums have culminated in tight complexity of $\tilde{O}((n+\sqrt{n L/μ})\log(1…