Search Results for author:
Found 11 papers, 0 papers with code
Generalization and Representational Limits of Graph Neural Networks
We address two fundamental questions about graph neural networks (GNNs).
Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization
Domain generalization is the problem of machine learning when the training data and the test data come from different data domains.
Multiresolution Transformer Networks: Recurrence is Not Essential for Modeling Hierarchical Structure
The architecture of Transformer is based entirely on self-attention, and has been shown to outperform models that employ recurrence on sequence transduction tasks such as machine translation.
Strategic Prediction with Latent Aggregative Games
We introduce a new class of context dependent, incomplete information games to serve as structured prediction models for settings with significant strategic interactions.
Solving graph compression via optimal transport
The transport problem is seeded with prior information about node importance, attributes, and edges in the graph.
Online Markov Decoding: Lower Bounds and Near-Optimal Approximation Algorithms
We resolve the fundamental problem of online decoding with general $n^{th}$ order ergodic Markov chain models.
Learning SMaLL Predictors
We present a new machine learning technique for training small resource-constrained predictors.
Supervising Unsupervised Learning
We introduce a framework to leverage knowledge acquired from a repository of (heterogeneous) supervised datasets to new unsupervised datasets.
Meta-Unsupervised-Learning: A supervised approach to unsupervised learning
We introduce a new paradigm to investigate unsupervised learning, reducing unsupervised learning to supervised learning.
CRAFT: ClusteR-specific Assorted Feature selecTion
We present a framework for clustering with cluster-specific feature selection.
DEEP-CARVING: Discovering Visual Attributes by Carving Deep Neural Nets
To ameliorate this limitation, we propose Deep-Carving, a novel training procedure with CNNs, that helps the net efficiently carve itself for the task of multiple attribute prediction.
