Maruan Al-Shedivat

(recent) selected papers [full list]

1. arXiv

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

   Al-Shedivat, M., Gillenwater, J., Xing, E., Rostamizadeh, A.

   arXiv preprint (in submission), 2020

   Abs arXiv Code

   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 formulate federated learning as a posterior inference problem, where the goal is to infer a global posterior distribution by having client devices each infer the posterior of their local data. While exact inference is often intractable, this perspective provides a principled way to search for global optima in federated settings. Further, starting with the analysis of federated quadratic objectives, we develop a computation- and communication-efficient approximate posterior inference algorithm – federated posterior averaging (FedPA). Our algorithm uses MCMC for approximate inference of local posteriors on the clients and efficiently communicates their statistics to the server, where the latter uses them to refine a global estimate of the posterior mode. Finally, we show that FedPA generalizes federated averaging (FedAvg), can similarly benefit from adaptive optimizers, and yields state-of-the-art results on four realistic and challenging benchmarks, converging faster, to better optima.

2. JMLR

   Contextual Explanation Networks

   Al-Shedivat, M., Dubey, A., Xing, E.P.

   Journal of Machine Learning Research (JMLR), 2020

   Abs arXiv PDF Code Press: NLP Highlights

   Modern learning algorithms excel at producing accurate but complex models of the data. However, deploying such models in the real-world requires extra care: we must ensure their reliability, robustness, and absence of undesired biases. This motivates the development of models that are equally accurate but can be also easily inspected and assessed beyond their predictive performance. To this end, we introduce contextual explanation networks (CENs)—a class of architectures that learn to predict by generating and utilizing intermediate, simplified probabilistic models. Specifically, CENs generate parameters for intermediate graphical models which are further used for prediction and play the role of explanations. Contrary to the existing post-hoc model-explanation tools, CENs learn to predict and to explain jointly. Our approach offers two major advantages: (i) for each prediction, valid, instance-specific explanations are generated with no computational overhead and (ii) prediction via explanation acts as a regularizer and boosts performance in low-resource settings. We analyze the proposed framework theoretically and experimentally. Our results on image and text classification and survival analysis tasks demonstrate that CENs are not only competitive with the state-of-the-art methods but also offer additional insights behind each prediction, that are valuable for decision support. We also show that while post-hoc methods may produce misleading explanations in certain cases, CENs are always consistent and allow to detect such cases systematically.

3. NAACL Full Oral

   Consistency by Agreement in Zero-shot Neural Machine Translation

   Al-Shedivat, M., Parikh, A.P.

   In Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2019

   Abs arXiv PDF Code Slides Talk

   Generalization and reliability of multilingual translation often highly depend on the amount of available parallel data for each language pair of interest. In this paper, we focus on zero-shot generalization—a challenging setup that tests models on translation directions they have not been optimized for at training time. To solve the problem, we (i) reformulate multilingual translation as probabilistic inference, (ii) define the notion of zero-shot consistency and show why standard training often results in models unsuitable for zero-shot tasks, and (iii) introduce a consistent agreement-based training method that encourages the model to produce equivalent translations of parallel sentences in auxiliary languages. We test our multilingual NMT models on multiple public zero-shot translation benchmarks (IWSLT17, UN corpus, Europarl) and show that agreement-based learning often results in 2-3 BLEU zero-shot improvement over strong baselines without any loss in performance on supervised translation directions.
4. ICLR Best Paper Award

   Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments

   Al-Shedivat, M., Bansal, T., Burda, Y., Sutskever, I., Mordatch, I., Abbeel, P.

   In International Conference on Learning Representations (ICLR), 2018

   Abs arXiv Blog Code Poster Talk Website Press: WIRED, Quartz

   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-learning algorithm suitable for adaptation in dynamically changing and adversarial scenarios. Additionally, we design a new multi-agent competitive environment, RoboSumo, and define iterated adaptation games for testing various aspects of continuous adaptation strategies. We demonstrate that meta-learning enables significantly more efficient adaptation than reactive baselines in the few-shot regime. Our experiments with a population of agents that learn and compete suggest that meta-learners are the fittest.