AIConfPaper
← Search

Maruan Al-Shedivat

12 accepted papers

2026

Triangle Multiplication is All You Need for Biomolecular Structure Representations

Jeffrey Ouyang-Zhang, Pranav Murugan, Daniel Jesus Diaz, Gianluca Scarpellini, Richard Strong Bowen, Nate Gruver +4
ICLR 2026poster

AlphaFold has transformed protein structure prediction, but emerging applications such as virtual ligand screening, proteome-wide folding, and de novo binder design demand predictions at a massive scale, where runtime and memory costs become prohibitive. A major bottleneck lies in the Pairformer bac…

Cited by 0Source ↗code ↗Scholar ↗
2021

Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithms

Maruan Al-Shedivat, Jennifer Gillenwater, Eric Xing, Afshin Rostamizadeh
ICLR 2021poster

Federated learning is typically approached as an optimization problem, where the goal is to minimize a global loss function by distributing computation across client devices that possess local data and specify different parts of the global objective. We present an alternative perspective and formul…

Cited by 146Source ↗PDF ↗code ↗Scholar ↗
2021

Knowledge-Aware Meta-learning for Low-Resource Text Classification

Huaxiu Yao, Ying-xin Wu, Maruan Al-Shedivat, Eric Xing
EMNLP 2021main

Meta-learning has achieved great success in leveraging the historical learned knowledge to facilitate the learning process of the new task. However, merely learning the knowledge from the historical tasks, adopted by current meta-learning algorithms, may not generalize well to testing tasks when the…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2021

Progressive Generation of Long Text with Pretrained Language Models

Bowen Tan, Zichao Yang, Maruan Al-Shedivat, Eric Xing, Zhiting Hu
NAACL 2021long

Large-scale language models (LMs) pretrained on massive corpora of text, such as GPT-2, are powerful open-domain text generators. However, as our systematic examination reveals, it is still challenging for such models to generate coherent long passages of text (e.g., 1000 tokens), especially when th…

Cited by 103Source ↗PDF ↗code ↗Scholar ↗
2020

Regularizing Black-box Models for Improved Interpretability

Gregory Plumb, Maruan Al-Shedivat, Ángel Alexander Cabrera, Adam Perer, Eric P. Xing, Ameet Talwalkar
NeurIPS 2020poster

Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post-hoc explanation systems, whose explanation quality can be unpredictable. Our method, ExpO, is a hybridization of these…

Cited by 69Source ↗PDF ↗code ↗Scholar ↗
2019

A Baseline for Any Order Gradient Estimation in Stochastic Computation Graphs

Jingkai Mao, Jakob Foerster, Tim Rocktäschel, Maruan Al-Shedivat, Gregory Farquhar, Shimon Whiteson
ICML 2019oral

By enabling correct differentiation in Stochastic Computation Graphs (SCGs), the infinitely differentiable Monte-Carlo estimator (DiCE) can generate correct estimates for the higher order gradients that arise in, e.g., multi-agent reinforcement learning and meta-learning. However, the baseline term…

Cited by 14Source ↗PDF ↗Scholar ↗
2018

Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments

Maruan Al-Shedivat, Trapit Bansal, Yura Burda, Ilya Sutskever, Igor Mordatch, Pieter Abbeel
ICLR 2018oral

Ability to continuously learn and adapt from limited experience in nonstationary environments is an important milestone on the path towards general intelligence. In this paper, we cast the problem of continuous adaptation into the learning-to-learn framework. We develop a simple gradient-based meta-…

Cited by 451Source ↗PDF ↗code ↗Scholar ↗
2018

DiCE: The Infinitely Differentiable Monte Carlo Estimator

Jakob Foerster, Gregory Farquhar, Maruan Al-Shedivat, Tim Rocktäschel, Eric Xing, Shimon Whiteson
ICML 2018oral

The score function estimator is widely used for estimating gradients of stochastic objectives in stochastic computation graphs (SCG), eg., in reinforcement learning and meta-learning. While deriving the first-order gradient estimators by differentiating a surrogate loss (SL) objective is computation…

Cited by 114Source ↗PDF ↗code ↗Scholar ↗
2018

Learning Policy Representations in Multiagent Systems

Aditya Grover, Maruan Al-Shedivat, Jayesh Gupta, Yuri Burda, Harrison Edwards
ICML 2018oral

Modeling agent behavior is central to understanding the emergence of complex phenomena in multiagent systems. Prior work in agent modeling has largely been task-specific and driven by hand-engineering domain-specific prior knowledge. We propose a general learning framework for modeling agent behavio…

Cited by 153Source ↗PDF ↗Scholar ↗
2016

Learning HMMs with Nonparametric Emissions via Spectral Decompositions of Continuous Matrices

Kirthevasan Kandasamy, Maruan Al-Shedivat, Eric P Xing
NeurIPS 2016poster

Recently, there has been a surge of interest in using spectral methods for estimating latent variable models. However, it is usually assumed that the distribution of the observations conditioned on the latent variables is either discrete or belongs to a parametric family. In this paper, we study the…

Cited by 7Source ↗PDF ↗code ↗Scholar ↗