In the post-Moore's Law era, relying solely on hardware advancements for...
Vector search has emerged as the foundation for large-scale information
...
Methods for carefully selecting or generating a small set of training da...
Applications of large open-domain knowledge graphs (KGs) to real-world
p...
There is an increasing adoption of machine learning for encoding data in...
We introduce Saga, a next-generation knowledge construction and serving
...
Graph Neural Networks (GNNs) have emerged as a powerful model for ML ove...
Structured data, or data that adheres to a pre-defined schema, can suffe...
We propose a new framework for computing the embeddings of large-scale g...
We show that state-of-the-art self-supervised language models can be rea...
Recent works show that overparameterized networks contain small subnetwo...
Record fusion is the task of aggregating multiple records that correspon...
Data corruption is an impediment to modern machine learning deployments....
Generalization Performance of Deep Learning models trained using the
Emp...
Data corruption, systematic or adversarial, may skew statistical estimat...
We study the problem of object detection over scanned images of scientif...
We study the problem of recovering the latent ground truth labeling of a...
Directed graphical models (DGMs) are a class of probabilistic models tha...
We study the problem of discovering functional dependencies (FD) from a ...
We introduce a few-shot learning framework for error detection. We show ...
Machine learning (ML) techniques are enjoying rapidly increasing adoptio...
Traditional modeling of inconsistency in database theory casts all possi...