828 citations · 5.6k across the 171 of their papers we have counts for
15 papers · 1 filter
Fundamental Limits and Tradeoffs in Invariant Representation Learning
Han Zhao, Chen Dan, Bryon Aragam +3
A wide range of machine learning applications such as privacy-preserving learning, algorithmic fairness, and domain adaptation/generalization among others, involve learning invaria…
Discovering Synergistic Drug Combinations for COVID with Biological Bottleneck Models
Wengong Jin, Regina Barzilay, Tommi Jaakkola
Drug combinations play an important role in therapeutics due to its better efficacy and reduced toxicity. Recent approaches have applied machine learning to identify synergistic co…
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…
Efficient Conformal Prediction via Cascaded Inference with Expanded Admission
Adam Fisch, Tal Schuster, Tommi Jaakkola +1
In this paper, we present a novel approach for conformal prediction (CP), in which we aim to identify a set of promising prediction candidates -- in place of a single prediction. T…
Improved Conditional Flow Models for Molecule to Image Synthesis
Karren Yang, Samuel Goldman, Wengong Jin +4
In this paper, we aim to synthesize cell microscopy images under different molecular interventions, motivated by practical applications to drug development. Building on the recent…
Optimal Transport Graph Neural Networks
Benson Chen, Gary Bécigneul, Octavian-Eugen Ganea +2
Current graph neural network (GNN) architectures naively average or sum node embeddings into an aggregated graph representation -- potentially losing structural or semantic informa…
Enforcing Predictive Invariance across Structured Biomedical Domains
Wengong Jin, Regina Barzilay, Tommi Jaakkola
Many biochemical applications such as molecular property prediction require models to generalize beyond their training domains (environments). Moreover, natural environments in the…
Adaptive Invariance for Molecule Property Prediction
Wengong Jin, Regina Barzilay, Tommi Jaakkola
Effective property prediction methods can help accelerate the search for COVID-19 antivirals either through accurate in-silico screens or by effectively guiding on-going at-scale e…
Invariant Rationalization
Shiyu Chang, Yang Zhang, Mo Yu +1
Selective rationalization improves neural network interpretability by identifying a small subset of input features -- the rationale -- that best explains or supports the prediction…
The Benefits of Pairwise Discriminators for Adversarial Training
Shangyuan Tong, Timur Garipov, Tommi Jaakkola
Adversarial training methods typically align distributions by solving two-player games. However, in most current formulations, even if the generator aligns perfectly with data, a s…
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…
Improving Molecular Design by Stochastic Iterative Target Augmentation
Kevin Yang, Wengong Jin, Kyle Swanson +2
Generative models in molecular design tend to be richly parameterized, data-hungry neural models, as they must create complex structured objects as outputs. Estimating such models…
Multi-Objective Molecule Generation using Interpretable Substructures
Wengong Jin, Regina Barzilay, Tommi Jaakkola
Drug discovery aims to find novel compounds with specified chemical property profiles. In terms of generative modeling, the goal is to learn to sample molecules in the intersection…
Hierarchical Generation of Molecular Graphs using Structural Motifs
Wengong Jin, Regina Barzilay, Tommi Jaakkola
Graph generation techniques are increasingly being adopted for drug discovery. Previous graph generation approaches have utilized relatively small molecular building blocks such as…
Blank Language Models
Tianxiao Shen, Victor Quach, Regina Barzilay +1
We propose Blank Language Model (BLM), a model that generates sequences by dynamically creating and filling in blanks. The blanks control which part of the sequence to expand, maki…