Jump to Content
Blaise Aguera y Arcas

Blaise Aguera y Arcas

Blaise leads Cerebra, a Google Research organization working on both basic research and new products. Among the team’s public contributions are MobileNets, Federated Learning, Coral, and many Android and Pixel AI features; they also founded the Artists and Machine Intelligence program. Until 2014 Blaise was a Distinguished Engineer at Microsoft, where he worked in a variety of roles, from inventor to strategist, and led teams with strengths in experience design, pro­to­typ­ing, machine vision, augmented reality, wearable com­put­ing and mapping. Blaise has given TED talks on Sead­ragon and Pho­to­synth (2007, 2012), Bing Maps (2010), and machine creativity (2016). In 2008, he was awarded MIT’s TR35 prize.
Authored Publications
Google Publications
Other Publications
Sort By
  • Title
  • Title, desc
  • Year
  • Year, desc
    Towards Generalist Biomedical AI
    Andrew Carroll
    Basil Mustafa
    Bradley Green
    Chuck Lau
    Danny Driess
    Ewa Dominowska
    Ira Ktena
    Joelle Barral
    Philip Mansfield
    Renee Wong
    Ryutaro Tanno
    Sara Mahdavi
    Simon Kornblith
    Sunny Virmani
    Sushant Prakash
    arxiv (2023)
    Preview abstract Medicine is inherently multimodal, with data spanning rich modalities including text, imaging, medical records, genomics, and more. Generalist biomedical AI systems that can flexibly encode, interpret, and integrate such data at scale can potentially enable impactful applications spanning care delivery and fundamental scientific discovery. We first curate MultiMedBench, a new multimodal biomedical benchmark to enable the development of such generalist models. MultiMedBench spans 14 diverse tasks including medical question answering, mammography and dermatology image interpretation, chest x-ray report generation and summarization and genomics variant calling. We then introduce Med-PaLM M (multimodal) - our proof of concept for such a generalist biomedical AI system. Med-PaLM M, built on top of PaLM-E, a large multimodal language model, flexibly encodes and interprets biomedical data spanning clinical language, medical imaging and genomics and can competently perform a diverse array of tasks with the same set of model weights. Med-PaLM M reaches performance near or exceeding the state-of-the-art (SOTA) on all tasks in MultiMedBench often beating task-specific narrow models by a wide margin. In addition, we also show qualitative examples of zero-shot learning, cross-task transfer learning and generalization with Med-PaLM M. In order to further probe the capabilities and limitations of Med-PaLM M, we propose an expert radiologist evaluation framework to characterize the quality of the chest x-ray radiology reports generated by the models. Under this framework, we observe encouraging quality of reports across model scales although remaining inferior to expert clinicians. Overall, while there are still several key limitations, we believe these results represent an important milestone towards the development of generalist biomedical AI systems. View details
    Large Language Models Encode Clinical Knowledge
    Sara Mahdavi
    Jason Wei
    Hyung Won Chung
    Nathan Scales
    Ajay Tanwani
    Heather Cole-Lewis
    Perry Payne
    Martin Seneviratne
    Paul Gamble
    Abubakr Abdelrazig Hassan Babiker
    Nathanael Schaerli
    Philip Mansfield
    Dina Demner-Fushman
    Katherine Chou
    Juraj Gottweis
    Nenad Tomašev
    Alvin Rajkomar
    Joelle Barral
    Nature (2023)
    Preview abstract Large language models (LLMs) have demonstrated impressive capabilities, but the bar for clinical applications is high. Attempts to assess the clinical knowledge of models typically rely on automated evaluations based on limited benchmarks. Here, to address these limitations, we present MultiMedQA, a benchmark combining six existing medical question answering datasets spanning professional medicine, research and consumer queries and a new dataset of medical questions searched online, HealthSearchQA. We propose a human evaluation framework for model answers along multiple axes including factuality, comprehension, reasoning, possible harm and bias. In addition, we evaluate Pathways Language Model1 (PaLM, a 540-billion parameter LLM) and its instruction-tuned variant, Flan-PaLM2 on MultiMedQA. Using a combination of prompting strategies, Flan-PaLM achieves state-of-the-art accuracy on every MultiMedQA multiple-choice dataset (MedQA3, MedMCQA4, PubMedQA5 and Measuring Massive Multitask Language Understanding (MMLU) clinical topics6), including 67.6% accuracy on MedQA (US Medical Licensing Exam-style questions), surpassing the prior state of the art by more than 17%. However, human evaluation reveals key gaps. To resolve this, we introduce instruction prompt tuning, a parameter-efficient approach for aligning LLMs to new domains using a few exemplars. The resulting model, Med-PaLM, performs encouragingly, but remains inferior to clinicians. We show that comprehension, knowledge recall and reasoning improve with model scale and instruction prompt tuning, suggesting the potential utility of LLMs in medicine. Our human evaluations reveal limitations of today’s models, reinforcing the importance of both evaluation frameworks and method development in creating safe, helpful LLMs for clinical applications. View details
    LaMDA: Language Models for Dialog Applications
    Aaron Daniel Cohen
    Alena Butryna
    Alicia Jin
    Apoorv Kulshreshtha
    Ben Zevenbergen
    Chung-ching Chang
    Cosmo Du
    Daniel De Freitas Adiwardana
    Dehao Chen
    Dmitry (Dima) Lepikhin
    Erin Hoffman-John
    Igor Krivokon
    James Qin
    Jamie Hall
    Joe Fenton
    Johnny Soraker
    Maarten Paul Bosma
    Marc Joseph Pickett
    Marcelo Amorim Menegali
    Marian Croak
    Maxim Krikun
    Noam Shazeer
    Rachel Bernstein
    Ravi Rajakumar
    Ray Kurzweil
    Romal Thoppilan
    Steven Zheng
    Taylor Bos
    Toju Duke
    Tulsee Doshi
    Vincent Y. Zhao
    Will Rusch
    Yuanzhong Xu
    arXiv (2022)
    Preview abstract We present LaMDA: Language Models for Dialog Applications. LaMDA is a family of Transformer-based neural language models specialized for dialog, which have up to 137B parameters and arepre-trained on 1.56T words of public dialog data and web text. While model scaling alone canimprove quality, it shows less improvements on safety and factual grounding. We demonstrate thatfine-tuning with annotated data and enabling the model to consult external knowledge sources canlead to significant improvements towards the two key challenges of safety and factual grounding.The first challenge, safety, involves ensuring that the model’s responses are consistent with a set ofhuman values, such as preventing harmful suggestions and unfair bias. We quantify safety using ametric based on an illustrative set of values, and we find that filtering candidate responses using aLaMDA classifier fine-tuned with a small amount of crowdworker-annotated data offers a promisingapproach to improving model safety. The second challenge, factual grounding, involves enabling themodel to consult external knowledge sources, such as an information retrieval system, a languagetranslator, and a calculator. We quantify factuality using a groundedness metric, and we find that ourapproach enables the model to generate responses grounded in known sources, rather than responsesthat merely sound plausible. Finally, we explore the use of LaMDA in the domains of education andcontent recommendations, and analyze their helpfulness and role consistency. View details
    A Field Guide to Federated Optimization
    Jianyu Wang
    Gauri Joshi
    Maruan Al-Shedivat
    Galen Andrew
    A. Salman Avestimehr
    Katharine Daly
    Deepesh Data
    Suhas Diggavi
    Hubert Eichner
    Advait Gadhikar
    Antonious M. Girgis
    Filip Hanzely
    Chaoyang He
    Samuel Horvath
    Martin Jaggi
    Tara Javidi
    Sai Praneeth Karimireddy
    Jakub Konečný
    Sanmi Koyejo
    Tian Li
    Peter Richtarik
    Virginia Smith
    Mahdi Soltanolkotabi
    Weikang Song
    Sebastian Stich
    Ameet Talwalkar
    Hongyi Wang
    Blake Woodworth
    Honglin Yuan
    Mi Zhang
    Tong Zhang
    Chunxiang (Jake) Zheng
    Chen Zhu
    arxiv (2021)
    Preview abstract Federated learning and analytics are a distributed approach for collaboratively learning models (or statistics) from decentralized data, motivated by and designed for privacy protection. The distributed learning process can be formulated as solving federated optimization problems, which emphasize communication efficiency, data heterogeneity, compatibility with privacy and system requirements, and other constraints that are not primary considerations in other problem settings. This paper provides recommendations and guidelines on formulating, designing, evaluating and analyzing federated optimization algorithms through concrete examples and practical implementation, with a focus on conducting effective simulations to infer real-world performance. The goal of this work is not to survey the current literature, but to inspire researchers and practitioners to design federated learning algorithms that can be used in various practical applications. View details
    Privacy-first Health Research with Federated Learning
    Adam Sadilek
    Dung Nguyen
    Methun Kamruzzaman
    Benjamin Rader
    Stefan Mellem
    Elaine O. Nsoesie
    Jamie MacFarlane
    Anil Vullikanti
    Madhav Marathe
    Paul C. Eastham
    John S. Brownstein
    John Hernandez
    npj Digital Medicine (2021)
    Preview abstract Privacy protection is paramount in conducting health research. However, studies often rely on data stored in a centralized repository, where analysis is done with full access to the sensitive underlying content. Recent advances in federated learning enable building complex machine-learned models that are trained in a distributed fashion. These techniques facilitate the calculation of research study endpoints such that private data never leaves a given device or healthcare system. We show—on a diverse set of single and multi-site health studies—that federated models can achieve similar accuracy, precision, and generalizability, and lead to the same interpretation as standard centralized statistical models while achieving considerably stronger privacy protections and without significantly raising computational costs. This work is the first to apply modern and general federated learning methods that explicitly incorporate differential privacy to clinical and epidemiological research—across a spectrum of units of federation, model architectures, complexity of learning tasks and diseases. As a result, it enables health research participants to remain in control of their data and still contribute to advancing science—aspects that used to be at odds with each other. View details
    UIBert: Learning Generic Multimodal Representations for UI Understanding
    Chongyang Bai
    Srinivas Kumar Sunkara
    Xiaoxue Zang
    Ying Xu
    the 30th International Joint Conference on Artificial Intelligence (IJCAI-21) (2021)
    Preview abstract To improve the accessibility of smart devices and to simplify their usage, building models which understand user interfaces (UIs) and assist users to complete their tasks is critical. However, unique challenges are proposed by UI-specific characteristics, such as how to effectively leverage multimodal UI features that involve image, text, and structural metadata and how to achieve good performance when high-quality labeled data is unavailable. To address such challenges we introduce UIBert, a transformer-based joint image-text model trained through novel pre-training tasks on large-scale unlabeled UI data to learn generic feature representations for a UI and its components. Our key intuition is that the heterogeneous features in a UI are self-aligned, i.e., the image and text features of UI components, are predictive of each other. We propose five pretraining tasks utilizing this self-alignment among different features of a UI component and across various components in the same UI. We evaluate our method on nine real-world downstream UI tasks where UIBert outperforms strong multimodal baselines by up to 9.26% accuracy. View details
    Preview abstract In this paper, we introduce a new type of generalized neural network where neurons and synapses maintain multiple states. We show that classical gradient-based backpropagation in neural networks can be seen as a special case of a two-state network where one state is used for activations and another for gradients, with update rules derived from the chain rule. In our generalized framework, networks have neither explicit notion of nor ever receive gradients. The synapses and neurons are updated using a bidirectional Hebb-style update rule parameterized by a shared low-dimensional "genome". We show that such genomes can be meta-learned from scratch, using either conventional optimization techniques, or evolutionary strategies, such as CMA-ES. Resulting update rules generalize to unseen tasks and train faster than gradient descent based optimizers for several standard computer vision and synthetic tasks. View details
    Preview abstract As mobile devices are becoming ubiquitous, regularly interacting with a variety of user interfaces (UIs) is a common aspect of daily life for many people. To improve the accessibility of these devices and to enable their usage in a variety of settings, building models that can assist users and accomplish tasks through the UI is vitally important. However, there are several challenges to achieve this. First, UI components of similar appearance can have different functionalities, making understanding their function more important than just analyzing their appearance. Second, domain-specific features like Document Object Model (DOM) in web pages and View Hierarchy (VH) in mobile applications provide important signals about the semantics of UI elements, but these features are not in a natural language format. Third, owing to a large diversity in UIs and absence of standard DOM or VH representations, building a UI understanding model with high coverage requires large amounts of training data. Inspired by the success of pre-training based approaches in NLP for tackling a variety of problems in a data-efficient way, we introduce a new pre-trained UI representation model called ActionBert. Our methodology is designed to leverage visual, linguistic and domain-specific features in user interaction traces to pre-train generic feature representations of UIs and their components. Our key intuition is that user actions, e.g., a sequence of clicks on different UI components, reveals important information about their functionality. We evaluate the proposed model on a wide variety of downstream tasks, ranging from icon classification to UI component retrieval based on its natural language description. Experiments show that the proposed ActionBert model outperforms multi-modal baselines across all downstream tasks by up to 15.5%. View details
    Preview abstract To improve real-world applications of machine learning, experienced modelers develop intuition about their datasets, their models, and how the two interact. Manual inspection of raw data—of representative samples, of outliers, of misclassifications—is an essential tool in a) identifying and fixing problems in the data, b) generating new modeling hypotheses, and c) assigning or refining human-provided labels. However, manual data inspection is risky for privacy-sensitive datasets, such as those representing the behavior of real-world individuals. Furthermore, manual data inspection is impossible in the increasingly important setting of federated learning, where raw examples are stored at the edge and the modeler may only access aggregated outputs such as metrics or model parameters. This paper demonstrates that generative models—trained using federated methods and with formal differential privacy guarantees—can be used effectively to debug data issues even when the data cannot be directly inspected. We explore these methods in applications to text with differentially private federated RNNs and to images using a novel algorithm for differentially private federated GANs. View details
    Communication-Efficient Learning of Deep Networks from Decentralized Data
    Eider Moore
    Seth Hampson
    Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS) (2017)
    Preview abstract Modern mobile devices have access to a wealth of data suitable for learning models, which in turn can greatly improve the user experience on the device. For example, language models can improve speech recognition and text entry, and image models can automatically select good photos. However, this rich data is often privacy sensitive, large in quantity, or both, which may preclude logging to the data center and training there using conventional approaches. We advocate an alternative that leaves the training data distributed on the mobile devices, and learns a shared model by aggregating locally-computed updates. We term this decentralized approach Federated Learning. We present a practical method for the federated learning of deep networks based on iterative model averaging, and conduct an extensive empirical evaluation, considering five different model architectures and four datasets. These experiments demonstrate the approach is robust to the unbalanced and non-IID data distributions that are a defining characteristic of this setting. Communication costs are the principal constraint, and we show a reduction in required communication rounds by 10-100x as compared to synchronized stochastic gradient descent. View details
    Preview abstract Existing music recognition applications require both user activation and a connection to a server that performs the actual recognition. In this paper we present a low power music recognizer that runs entirely on a mobile phone and automatically recognizes music without requiring any user activation. A small music detector runs continuously on the mobile phone’s DSP (digital signal processor) chip and only wakes main the processor when it is confident that music is present. Once woken the detector on the main processor is provided with an 8s buffer of audio which is then fingerprinted and compared to the stored fingerprints in the on-device fingerprint database of over 70000 songs. View details
    No Results Found