Search Results for author: Tommi Jaakkola

Found 112 papers, 65 papers with code

Predicting deliberative outcomes

no code implementations ICML 2020 Vikas Garg, Tommi Jaakkola

Our games take as input, e. g., UN resolution to be voted on, and map such contexts to initial strategies, player utilities, and interactions.

Structured Prediction

Composing Molecules with Multiple Property Constraints

no code implementations ICML 2020 Wengong Jin, Regina Barzilay, Tommi Jaakkola

These rationales are identified from molecules as substructures that are likely responsible for each property of interest.

Drug Discovery

Predicting deliberative outcomes

no code implementations ICML 2020 Vikas Garg, Tommi Jaakkola

Our games take as input, e. g., UN resolution to be voted on, and map such contexts to initial strategies, player utilities, and interactions.

Structured Prediction

Dirichlet Flow Matching with Applications to DNA Sequence Design

1 code implementation8 Feb 2024 Hannes Stark, Bowen Jing, Chenyu Wang, Gabriele Corso, Bonnie Berger, Regina Barzilay, Tommi Jaakkola

Further, we provide distilled Dirichlet flow matching, which enables one-step sequence generation with minimal performance hits, resulting in $O(L)$ speedups compared to autoregressive models.

AlphaFold Meets Flow Matching for Generating Protein Ensembles

1 code implementation7 Feb 2024 Bowen Jing, Bonnie Berger, Tommi Jaakkola

When trained and evaluated on the PDB, our method provides a superior combination of precision and diversity compared to AlphaFold with MSA subsampling.

Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design

1 code implementation7 Feb 2024 Andrew Campbell, Jason Yim, Regina Barzilay, Tom Rainforth, Tommi Jaakkola

Our approach achieves state-of-the-art co-design performance while allowing the same multimodal model to be used for flexible generation of the sequence or structure.

Sample, estimate, aggregate: A recipe for causal discovery foundation models

1 code implementation2 Feb 2024 Menghua Wu, Yujia Bao, Regina Barzilay, Tommi Jaakkola

Causal discovery, the task of inferring causal structure from data, promises to accelerate scientific research, inform policy making, and more.

Causal Discovery

Correcting Diffusion Generation through Resampling

1 code implementation10 Dec 2023 Yujian Liu, Yang Zhang, Tommi Jaakkola, Shiyu Chang

Despite diffusion models' superior capabilities in modeling complex distributions, there are still non-trivial distributional discrepancies between generated and ground-truth images, which has resulted in several notable problems in image generation, including missing object errors in text-to-image generation and low image quality.

Object

Equivariant Scalar Fields for Molecular Docking with Fast Fourier Transforms

1 code implementation7 Dec 2023 Bowen Jing, Tommi Jaakkola, Bonnie Berger

The runtime of our approach can be amortized at several levels of abstraction, and is particularly favorable for virtual screening settings with a common binding pocket.

Molecular Docking

Fast non-autoregressive inverse folding with discrete diffusion

1 code implementation5 Dec 2023 John J. Yang, Jason Yim, Regina Barzilay, Tommi Jaakkola

Generating protein sequences that fold into a intended 3D structure is a fundamental step in de novo protein design.

Protein Design

Risk-Controlling Model Selection via Guided Bayesian Optimization

no code implementations4 Dec 2023 Bracha Laufer-Goldshtein, Adam Fisch, Regina Barzilay, Tommi Jaakkola

Adjustable hyperparameters of machine learning models typically impact various key trade-offs such as accuracy, fairness, robustness, or inference cost.

Bayesian Optimization Fairness +1

Removing Biases from Molecular Representations via Information Maximization

1 code implementation1 Dec 2023 Chenyu Wang, Sharut Gupta, Caroline Uhler, Tommi Jaakkola

High-throughput drug screening -- using cell imaging or gene expression measurements as readouts of drug effect -- is a critical tool in biotechnology to assess and understand the relationship between the chemical structure and biological activity of a drug.

Fairness Molecular Property Prediction +2

Learning Interatomic Potentials at Multiple Scales

no code implementations20 Oct 2023 Xiang Fu, Albert Musaelian, Anders Johansson, Tommi Jaakkola, Boris Kozinsky

When running MD, the MTS integrator then evaluates the smaller model for every time step and the larger model less frequently, accelerating simulation.

Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models

1 code implementation19 Oct 2023 Gabriele Corso, Yilun Xu, Valentin De Bortoli, Regina Barzilay, Tommi Jaakkola

In light of the widespread success of generative models, a significant amount of research has gone into speeding up their sampling time.

Conditional Image Generation

MOFDiff: Coarse-grained Diffusion for Metal-Organic Framework Design

no code implementations16 Oct 2023 Xiang Fu, Tian Xie, Andrew S. Rosen, Tommi Jaakkola, Jake Smith

Metal-organic frameworks (MOFs) are of immense interest in applications such as gas storage and carbon capture due to their exceptional porosity and tunable chemistry.

Denoising valid

Harmonic Self-Conditioned Flow Matching for Multi-Ligand Docking and Binding Site Design

1 code implementation9 Oct 2023 Hannes Stärk, Bowen Jing, Regina Barzilay, Tommi Jaakkola

A significant amount of protein function requires binding small molecules, including enzymatic catalysis.

Improving Protein Optimization with Smoothed Fitness Landscapes

1 code implementation2 Jul 2023 Andrew Kirjner, Jason Yim, Raman Samusevich, Shahar Bracha, Tommi Jaakkola, Regina Barzilay, Ila Fiete

The ability to engineer novel proteins with higher fitness for a desired property would be revolutionary for biotechnology and medicine.

Efficient Exploration

Restart Sampling for Improving Generative Processes

1 code implementation NeurIPS 2023 Yilun Xu, Mingyang Deng, Xiang Cheng, Yonglong Tian, Ziming Liu, Tommi Jaakkola

Restart not only outperforms the previous best SDE results, but also accelerates the sampling speed by 10-fold / 2-fold on CIFAR-10 / ImageNet $64 \times 64$.

Attribute

Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models

1 code implementation6 Apr 2023 Guanhua Zhang, Jiabao Ji, Yang Zhang, Mo Yu, Tommi Jaakkola, Shiyu Chang

COPAINT also uses the Bayesian framework to jointly modify both revealed and unrevealed regions, but approximates the posterior distribution in a way that allows the errors to gradually drop to zero throughout the denoising steps, thus strongly penalizing any mismatches with the reference image.

Denoising Image Inpainting

GenPhys: From Physical Processes to Generative Models

no code implementations5 Apr 2023 Ziming Liu, Di Luo, Yilun Xu, Tommi Jaakkola, Max Tegmark

We introduce a general family, Generative Models from Physical Processes (GenPhys), where we translate partial differential equations (PDEs) describing physical processes to generative models.

EigenFold: Generative Protein Structure Prediction with Diffusion Models

1 code implementation5 Apr 2023 Bowen Jing, Ezra Erives, Peter Pao-Huang, Gabriele Corso, Bonnie Berger, Tommi Jaakkola

Protein structure prediction has reached revolutionary levels of accuracy on single structures, yet distributional modeling paradigms are needed to capture the conformational ensembles and flexibility that underlie biological function.

Protein Structure Prediction

SE(3) diffusion model with application to protein backbone generation

1 code implementation5 Feb 2023 Jason Yim, Brian L. Trippe, Valentin De Bortoli, Emile Mathieu, Arnaud Doucet, Regina Barzilay, Tommi Jaakkola

The design of novel protein structures remains a challenge in protein engineering for applications across biomedicine and chemistry.

Protein Structure Prediction

Stable Target Field for Reduced Variance Score Estimation in Diffusion Models

1 code implementation1 Feb 2023 Yilun Xu, Shangyuan Tong, Tommi Jaakkola

We show that the procedure indeed helps in the challenging intermediate regime by reducing (the trace of) the covariance of training targets.

Denoising Image Generation

Is Conditional Generative Modeling all you need for Decision-Making?

no code implementations28 Nov 2022 Anurag Ajay, Yilun Du, Abhi Gupta, Joshua Tenenbaum, Tommi Jaakkola, Pulkit Agrawal

We further demonstrate the advantages of modeling policies as conditional diffusion models by considering two other conditioning variables: constraints and skills.

Decision Making Offline RL +1

Efficiently Controlling Multiple Risks with Pareto Testing

no code implementations14 Oct 2022 Bracha Laufer-Goldshtein, Adam Fisch, Regina Barzilay, Tommi Jaakkola

Machine learning applications frequently come with multiple diverse objectives and constraints that can change over time.

Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulations

1 code implementation13 Oct 2022 Xiang Fu, Zhenghao Wu, Wujie Wang, Tian Xie, Sinan Keten, Rafael Gomez-Bombarelli, Tommi Jaakkola

We benchmark a collection of state-of-the-art (SOTA) ML FF models and illustrate, in particular, how the commonly benchmarked force accuracy is not well aligned with relevant simulation metrics.

DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking

2 code implementations4 Oct 2022 Gabriele Corso, Hannes Stärk, Bowen Jing, Regina Barzilay, Tommi Jaakkola

We instead frame molecular docking as a generative modeling problem and develop DiffDock, a diffusion generative model over the non-Euclidean manifold of ligand poses.

Blind Docking

Poisson Flow Generative Models

1 code implementation22 Sep 2022 Yilun Xu, Ziming Liu, Max Tegmark, Tommi Jaakkola

We interpret the data points as electrical charges on the $z=0$ hyperplane in a space augmented with an additional dimension $z$, generating a high-dimensional electric field (the gradient of the solution to Poisson equation).

Image Generation

Calibrated Selective Classification

no code implementations25 Aug 2022 Adam Fisch, Tommi Jaakkola, Regina Barzilay

Providing calibrated uncertainty estimates alongside predictions -- probabilities that correspond to true frequencies -- can be as important as having predictions that are simply accurate on average.

Classification Image Classification

Antibody-Antigen Docking and Design via Hierarchical Equivariant Refinement

1 code implementation14 Jul 2022 Wengong Jin, Regina Barzilay, Tommi Jaakkola

The binding affinity is governed by the 3D binding interface where antibody residues (paratope) closely interact with antigen residues (epitope).

Atomic Forces

Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem

1 code implementation8 Jun 2022 Brian L. Trippe, Jason Yim, Doug Tischer, David Baker, Tamara Broderick, Regina Barzilay, Tommi Jaakkola

Construction of a scaffold structure that supports a desired motif, conferring protein function, shows promise for the design of vaccines and enzymes.

Subspace Diffusion Generative Models

1 code implementation3 May 2022 Bowen Jing, Gabriele Corso, Renato Berlinghieri, Tommi Jaakkola

Score-based models generate samples by mapping noise to data (and vice versa) via a high-dimensional diffusion process.

Denoising Image Generation

Conformal Prediction Sets with Limited False Positives

1 code implementation15 Feb 2022 Adam Fisch, Tal Schuster, Tommi Jaakkola, Regina Barzilay

We propose to trade coverage for a notion of precision by enforcing that the presence of incorrect candidates in the predicted conformal sets (i. e., the total number of false positives) is bounded according to a user-specified tolerance.

Conformal Prediction

Controlling Directions Orthogonal to a Classifier

1 code implementation ICLR 2022 Yilun Xu, Hao He, Tianxiao Shen, Tommi Jaakkola

We propose to identify directions invariant to a given classifier so that these directions can be controlled in tasks such as style transfer.

Domain Adaptation Fairness +1

Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking

1 code implementation ICLR 2022 Octavian-Eugen Ganea, Xinyuan Huang, Charlotte Bunne, Yatao Bian, Regina Barzilay, Tommi Jaakkola, Andreas Krause

Protein complex formation is a central problem in biology, being involved in most of the cell's processes, and essential for applications, e. g. drug design or protein engineering.

Graph Matching Translation

Fragment-based Sequential Translation for Molecular Optimization

no code implementations NeurIPS Workshop AI4Scien 2021 Benson Chen, Xiang Fu, Regina Barzilay, Tommi Jaakkola

Equipped with the learned fragment vocabulary, we propose Fragment-based Sequential Translation (FaST), which learns a reinforcement learning (RL) policy to iteratively translate model-discovered molecules into increasingly novel molecules while satisfying desired properties.

Drug Discovery Reinforcement Learning (RL) +1

Learning Representations that Support Robust Transfer of Predictors

2 code implementations19 Oct 2021 Yilun Xu, Tommi Jaakkola

We further demonstrate the impact of optimizing such transfer risk on two controlled settings, each representing a different pattern of environment shift, as well as on two real-world datasets.

Domain Generalization Out-of-Distribution Generalization

Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design

1 code implementation ICLR 2022 Wengong Jin, Jeremy Wohlwend, Regina Barzilay, Tommi Jaakkola

In this paper, we propose a generative model to automatically design the CDRs of antibodies with enhanced binding specificity or neutralization capabilities.

Protein Design Specificity

Learning Task Informed Abstractions

1 code implementation29 Jun 2021 Xiang Fu, Ge Yang, Pulkit Agrawal, Tommi Jaakkola

Current model-based reinforcement learning methods struggle when operating from complex visual scenes due to their inability to prioritize task-relevant features.

Model-based Reinforcement Learning reinforcement-learning +1

Mol2Image: Improved Conditional Flow Models for Molecule to Image Synthesis

no code implementations CVPR 2021 Karren Yang, Samuel Goldman, Wengong Jin, Alex X. Lu, Regina Barzilay, Tommi Jaakkola, Caroline Uhler

In this paper, we aim to synthesize cell microscopy images under different molecular interventions, motivated by practical applications to drug development.

Contrastive Learning Image Generation

Consistent Accelerated Inference via Confident Adaptive Transformers

1 code implementation EMNLP 2021 Tal Schuster, Adam Fisch, Tommi Jaakkola, Regina Barzilay

In this work, we present CATs -- Confident Adaptive Transformers -- in which we simultaneously increase computational efficiency, while guaranteeing a specifiable degree of consistency with the original model with high confidence.

Computational Efficiency Conformal Prediction +1

Few-shot Conformal Prediction with Auxiliary Tasks

1 code implementation17 Feb 2021 Adam Fisch, Tal Schuster, Tommi Jaakkola, Regina Barzilay

We develop a novel approach to conformal prediction when the target task has limited data available for training.

Conformal Prediction Drug Discovery +1

Discovering Synergistic Drug Combinations for COVID with Biological Bottleneck Models

no code implementations9 Nov 2020 Wengong Jin, Regina Barzilay, Tommi Jaakkola

Drug combinations play an important role in therapeutics due to its better efficacy and reduced toxicity.

Information Obfuscation of Graph Neural Networks

1 code implementation28 Sep 2020 Peiyuan Liao, Han Zhao, Keyulu Xu, Tommi Jaakkola, Geoffrey Gordon, Stefanie Jegelka, Ruslan Salakhutdinov

While the advent of Graph Neural Networks (GNNs) has greatly improved node and graph representation learning in many applications, the neighborhood aggregation scheme exposes additional vulnerabilities to adversaries seeking to extract node-level information about sensitive attributes.

Adversarial Defense Graph Representation Learning +2

Efficient Conformal Prediction via Cascaded Inference with Expanded Admission

1 code implementation ICLR 2021 Adam Fisch, Tal Schuster, Tommi Jaakkola, Regina Barzilay

This set is guaranteed to contain a correct answer with high probability, and is well-suited for many open-ended classification tasks.

Conformal Prediction Drug Discovery +2

Improved Conditional Flow Models for Molecule to Image Synthesis

1 code implementation15 Jun 2020 Karren Yang, Samuel Goldman, Wengong Jin, Alex Lu, Regina Barzilay, Tommi Jaakkola, Caroline Uhler

In this paper, we aim to synthesize cell microscopy images under different molecular interventions, motivated by practical applications to drug development.

Contrastive Learning Image Generation

Optimal Transport Graph Neural Networks

2 code implementations8 Jun 2020 Benson Chen, Gary Bécigneul, Octavian-Eugen Ganea, Regina Barzilay, Tommi Jaakkola

Current graph neural network (GNN) architectures naively average or sum node embeddings into an aggregated graph representation -- potentially losing structural or semantic information.

 Ranked #1 on Graph Regression on Lipophilicity (using extra training data)

Drug Discovery Graph Regression +2

Enforcing Predictive Invariance across Structured Biomedical Domains

no code implementations6 Jun 2020 Wengong Jin, Regina Barzilay, Tommi Jaakkola

We evaluate our method on multiple applications: molecular property prediction, protein homology and stability prediction and show that RGM significantly outperforms previous state-of-the-art baselines.

Domain Generalization Molecular Property Prediction +1

Adaptive Invariance for Molecule Property Prediction

no code implementations5 May 2020 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 experimental efforts.

Property Prediction Transfer Learning

Self-Supervised Learning of Appliance Usage

no code implementations ICLR 2020 Chen-Yu Hsu, Abbas Zeitoun, Guang-He Lee, Dina Katabi, Tommi Jaakkola

We show that this cross-modal prediction task allows us to detect when a particular appliance is used, and the location of the appliance in the home, all in a self-supervised manner, without any labeled data.

Event Detection Self-Supervised Learning +1

The Benefits of Pairwise Discriminators for Adversarial Training

1 code implementation20 Feb 2020 Shangyuan Tong, Timur Garipov, Tommi Jaakkola

We provide sufficient conditions for local convergence; characterize the capacity balance that should guide the discriminator and generator choices; and construct examples of minimally sufficient discriminators.

Improving Molecular Design by Stochastic Iterative Target Augmentation

2 code implementations ICML 2020 Kevin Yang, Wengong Jin, Kyle Swanson, Regina Barzilay, Tommi Jaakkola

The property predictor is then used as a likelihood model for filtering candidate structures from the generative model.

Program Synthesis

Multi-Objective Molecule Generation using Interpretable Substructures

2 code implementations8 Feb 2020 Wengong Jin, Regina Barzilay, Tommi Jaakkola

These rationales are identified from molecules as substructures that are likely responsible for each property of interest.

Drug Discovery

Blank Language Models

1 code implementation EMNLP 2020 Tianxiao Shen, Victor Quach, Regina Barzilay, Tommi Jaakkola

We propose Blank Language Model (BLM), a model that generates sequences by dynamically creating and filling in blanks.

Ancient Text Restoration Language Modelling +1

Generative Models for Graph-Based Protein Design

1 code implementation ICLR Workshop DeepGenStruct 2019 John Ingraham, Vikas Garg, Regina Barzilay, Tommi Jaakkola

Engineered proteins offer the potential to solve many problems in biomedicine, energy, and materials science, but creating designs that succeed is difficult in practice.

Protein Design Protein Folding

Direct Optimization through \arg \max for Discrete Variational Auto-Encoder

1 code implementation NeurIPS 2019 Guy Lorberbom, Tommi Jaakkola, Andreea Gane, Tamir Hazan

Reparameterization of variational auto-encoders with continuous random variables is an effective method for reducing the variance of their gradient estimates.

Iterative Target Augmentation for Effective Conditional Generation

no code implementations25 Sep 2019 Kevin Yang, Wengong Jin, Kyle Swanson, Regina Barzilay, Tommi Jaakkola

Many challenging prediction problems, from molecular optimization to program synthesis, involve creating complex structured objects as outputs.

Program Synthesis

Denoising Improves Latent Space Geometry in Text Autoencoders

no code implementations25 Sep 2019 Tianxiao Shen, Jonas Mueller, Regina Barzilay, Tommi Jaakkola

Neural language models have recently shown impressive gains in unconditional text generation, but controllable generation and manipulation of text remain challenging.

Denoising Sentence +1

Hierarchical Graph-to-Graph Translation for Molecules

1 code implementation11 Jun 2019 Wengong Jin, Regina Barzilay, Tommi Jaakkola

The problem of accelerating drug discovery relies heavily on automatic tools to optimize precursor molecules to afford them with better biochemical properties.

Drug Discovery Graph-To-Graph Translation +1

Solving graph compression via optimal transport

no code implementations NeurIPS 2019 Vikas K. Garg, Tommi Jaakkola

The transport problem is seeded with prior information about node importance, attributes, and edges in the graph.

General Classification Graph Classification

Educating Text Autoencoders: Latent Representation Guidance via Denoising

3 code implementations ICML 2020 Tianxiao Shen, Jonas Mueller, Regina Barzilay, Tommi Jaakkola

We prove that this simple modification guides the latent space geometry of the resulting model by encouraging the encoder to map similar texts to similar latent representations.

Denoising Sentence +2

Strategic Prediction with Latent Aggregative Games

no code implementations29 May 2019 Vikas K. Garg, Tommi Jaakkola

We introduce a new class of context dependent, incomplete information games to serve as structured prediction models for settings with significant strategic interactions.

Structured Prediction

Path-Augmented Graph Transformer Network

2 code implementations29 May 2019 Benson Chen, Regina Barzilay, Tommi Jaakkola

Much of the recent work on learning molecular representations has been based on Graph Convolution Networks (GCN).

Molecular Property Prediction Property Prediction

Alignment Based Mathching Networks for One-Shot Classification and Open-Set Recognition

no code implementations ICLR 2019 Paresh Malalur, Tommi Jaakkola

An attention mechanism can be used to highlight the area of the image that the model focuses on thus offering a narrow view into the mechanism of classification.

Classification General Classification +1

Learning Multimodal Graph-to-Graph Translation for Molecule Optimization

no code implementations ICLR 2019 Wengong Jin, Kevin Yang, Regina Barzilay, Tommi Jaakkola

We evaluate our model on multiple molecule optimization tasks and show that our model outperforms previous state-of-the-art baselines by a significant margin.

Graph-To-Graph Translation Translation

Analyzing Learned Molecular Representations for Property Prediction

4 code implementations2 Apr 2019 Kevin Yang, Kyle Swanson, Wengong Jin, Connor Coley, Philipp Eiden, Hua Gao, Angel Guzman-Perez, Timothy Hopper, Brian Kelley, Miriam Mathea, Andrew Palmer, Volker Settels, Tommi Jaakkola, Klavs Jensen, Regina Barzilay

In addition, we introduce a graph convolutional model that consistently matches or outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary datasets.

Molecular Property Prediction molecular representation +1

Alignment Based Matching Networks for One-Shot Classification and Open-Set Recognition

no code implementations11 Mar 2019 Paresh Malalur, Tommi Jaakkola

An attention mechanism can be used to highlight the area of the image that the model focuses on thus offering a narrow view into the mechanism of classification.

Classification General Classification +1

Learning Multimodal Graph-to-Graph Translation for Molecular Optimization

5 code implementations3 Dec 2018 Wengong Jin, Kevin Yang, Regina Barzilay, Tommi Jaakkola

We evaluate our model on multiple molecular optimization tasks and show that our model outperforms previous state-of-the-art baselines.

Graph-To-Graph Translation Translation

Towards Robust Interpretability with Self-Explaining Neural Networks

2 code implementations NeurIPS 2018 David Alvarez Melis, Tommi Jaakkola

Most recent work on interpretability of complex machine learning models has focused on estimating a-posteriori explanations for previously trained models around specific predictions.

The Variational Homoencoder: Learning to learn high capacity generative models from few examples

1 code implementation24 Jul 2018 Luke B. Hewitt, Maxwell I. Nye, Andreea Gane, Tommi Jaakkola, Joshua B. Tenenbaum

However, when this generative model is expressed as a powerful neural network such as a PixelCNN, we show that existing learning techniques typically fail to effectively use latent variables.

General Classification Test

Direct Optimization through $\arg \max$ for Discrete Variational Auto-Encoder

2 code implementations ICLR 2019 Guy Lorberbom, Andreea Gane, Tommi Jaakkola, Tamir Hazan

We demonstrate empirically the effectiveness of the direct loss minimization technique in variational autoencoders with both unstructured and structured discrete latent variables.

The Variational Homoencoder: Learning to Infer High-Capacity Generative Models from Few Examples

no code implementations ICLR 2018 Luke Hewitt, Andrea Gane, Tommi Jaakkola, Joshua B. Tenenbaum

Hierarchical Bayesian methods have the potential to unify many related tasks (e. g. k-shot classification, conditional, and unconditional generation) by framing each as inference within a single generative model.

General Classification Test

Local Aggregative Games

no code implementations NeurIPS 2017 Vikas Garg, Tommi Jaakkola

Aggregative games provide a rich abstraction to model strategic multi-agent interactions.

Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network

1 code implementation NeurIPS 2017 Wengong Jin, Connor W. Coley, Regina Barzilay, Tommi Jaakkola

The prediction of organic reaction outcomes is a fundamental problem in computational chemistry.

Grounding Language for Transfer in Deep Reinforcement Learning

1 code implementation1 Aug 2017 Karthik Narasimhan, Regina Barzilay, Tommi Jaakkola

In this paper, we explore the utilization of natural language to drive transfer for reinforcement learning (RL).

reinforcement-learning Reinforcement Learning (RL)

Sequence to Better Sequence: Continuous Revision of Combinatorial Structures

no code implementations ICML 2017 Jonas Mueller, David Gifford, Tommi Jaakkola

Under this model, gradient methods can be used to efficiently optimize the continuous latent factors with respect to inferred outcomes.

Style Transfer from Non-Parallel Text by Cross-Alignment

12 code implementations NeurIPS 2017 Tianxiao Shen, Tao Lei, Regina Barzilay, Tommi Jaakkola

We demonstrate the effectiveness of this cross-alignment method on three tasks: sentiment modification, decipherment of word substitution ciphers, and recovery of word order.

Decipherment Machine Translation +3

Deriving Neural Architectures from Sequence and Graph Kernels

no code implementations ICML 2017 Tao Lei, Wengong Jin, Regina Barzilay, Tommi Jaakkola

The design of neural architectures for structured objects is typically guided by experimental insights rather than a formal process.

Graph Regression Language Modelling +1

Aspect-augmented Adversarial Networks for Domain Adaptation

1 code implementation TACL 2017 Yuan Zhang, Regina Barzilay, Tommi Jaakkola

We introduce a neural method for transfer learning between two (source and target) classification tasks or aspects over the same domain.

Domain Adaptation General Classification +2

Learning Tree Structured Potential Games

no code implementations NeurIPS 2016 Vikas Garg, Tommi Jaakkola

Many real phenomena, including behaviors, involve strategic interactions that can be learned from data.

Learning Optimal Interventions

no code implementations16 Jun 2016 Jonas Mueller, David N. Reshef, George Du, Tommi Jaakkola

Assuming the underlying relationship remains invariant under intervention, we develop efficient algorithms to identify the optimal intervention policy from limited data and provide theoretical guarantees for our approach in a Gaussian Process setting.

Rationalizing Neural Predictions

3 code implementations EMNLP 2016 Tao Lei, Regina Barzilay, Tommi Jaakkola

Our approach combines two modular components, generator and encoder, which are trained to operate well together.

Retrieval Sentiment Analysis +1

High Dimensional Inference with Random Maximum A-Posteriori Perturbations

no code implementations10 Feb 2016 Tamir Hazan, Francesco Orabona, Anand D. Sarwate, Subhransu Maji, Tommi Jaakkola

This paper shows that the expected value of perturb-max inference with low dimensional perturbations can be used sequentially to generate unbiased samples from the Gibbs distribution.

Vocal Bursts Intensity Prediction

Semi-supervised Question Retrieval with Gated Convolutions

1 code implementation NAACL 2016 Tao Lei, Hrishikesh Joshi, Regina Barzilay, Tommi Jaakkola, Katerina Tymoshenko, Alessandro Moschitti, Lluis Marquez

Question answering forums are rapidly growing in size with no effective automated ability to refer to and reuse answers already available for previous posted questions.

Question Answering Retrieval

Steps Toward Deep Kernel Methods from Infinite Neural Networks

no code implementations20 Aug 2015 Tamir Hazan, Tommi Jaakkola

Contemporary deep neural networks exhibit impressive results on practical problems.

Gaussian Processes

Structured Prediction: From Gaussian Perturbations to Linear-Time Principled Algorithms

no code implementations5 Aug 2015 Jean Honorio, Tommi Jaakkola

Thus, using the maximum loss over random structured outputs is a principled way of learning the parameter of structured prediction models.

Structured Prediction

An Unsupervised Method for Uncovering Morphological Chains

1 code implementation TACL 2015 Karthik Narasimhan, Regina Barzilay, Tommi Jaakkola

In contrast, we propose a model for unsupervised morphological analysis that integrates orthographic and semantic views of words.

Morphological Analysis

Controlling privacy in recommender systems

no code implementations NeurIPS 2014 Yu Xin, Tommi Jaakkola

Recommender systems involve an inherent trade-off between accuracy of recommendations and the extent to which users are willing to release information about their preferences.

Recommendation Systems

On Measure Concentration of Random Maximum A-Posteriori Perturbations

no code implementations15 Oct 2013 Francesco Orabona, Tamir Hazan, Anand D. Sarwate, Tommi Jaakkola

Applying the general result to MAP perturbations can yield a more efficient algorithm to approximate sampling from the Gibbs distribution.

Proceedings of the Twenty-First Conference on Uncertainty in Artificial Intelligence (2005)

no code implementations25 Aug 2012 Fahiem Bacchus, Tommi Jaakkola

This is the Proceedings of the Twenty-First Conference on Uncertainty in Artificial Intelligence, which was held in Edinburgh, Scotland July 26 - 29 2005.

Cannot find the paper you are looking for? You can Submit a new open access paper.