Publications
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Sort By
1 - 15 of 10132 publications
Preview abstract
In this paper, we present SCOREQ, a novel approach for speech quality prediction. SCOREQ is a triplet loss function for contrastive regression that addresses the domain generalisation shortcoming exhibited by state of the art no-reference speech quality metrics. In the paper we: (i) illustrate the problem of L2 loss training failing at capturing the continuous nature of the mean opinion score (MOS) labels; (ii) demonstrate the lack of generalisation through a benchmarking evaluation across several speech domains; (iii) outline our approach and explore the impact of the architectural design decisions through incremental evaluation; (iv) evaluate the final model against state of the art models for a wide variety of data and domains. The results show that the lack of generalisation observed in state of the art speech quality metrics is addressed by SCOREQ. We conclude that using a triplet loss function
View details
Resolving Code Review Comments with Machine Learning
Alexander Frömmgen
Peter Choy
Elena Khrapko
Marcus Revaj
2024 IEEE/ACM 46th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) (to appear)
Preview abstract
Code reviews are a critical part of the software development process, taking a significant amount of the code authors’ and the code reviewers’ time. As part of this process, the reviewer inspects the proposed code and asks the author for code changes through comments written in natural language. At Google, we see millions of reviewer comments per year, and authors require an average of ∼60 minutes active shepherding time between sending changes for review and finally submitting the change. In our measurements, the required active work time that the code author must devote to address reviewer comments grows almost linearly with the number of comments. However, with machine learning (ML), we have an opportunity to automate and streamline the code-review process, e.g., by proposing code changes based on a comment’s text.
We describe our application of recent advances in large sequence models in a real-world setting to automatically resolve code-review comments in the day-to-day development workflow at Google. We present the evolution of this feature from an asynchronous generation of suggested edits after the reviewer sends feedback, to an interactive experience that suggests code edits to the reviewer at review time. In deployment, code-change authors at Google address 7.5% of all reviewer comments by applying an ML-suggested edit. The impact of this will be to reduce the time spent on code reviews by hundreds of thousands of engineer hours annually at Google scale. Unsolicited, very positive feedback highlights that the impact of ML-suggested code edits increases Googlers’ productivity and allows them to focus on more creative and complex tasks.
View details
Preview abstract
Background. Wildfire research uses ensemble methods to analyze fire behaviors and assess
uncertainties. Nonetheless, current research methods are either confined to simple models
or complex simulations with limits. Modern computing tools could allow for efficient, high-
fidelity ensemble simulations. Aims. This study proposes a high-fidelity ensemble wildfire
simulation framework for studying wildfire behavior, ML tasks, fire-risk assessment, and
uncertainty analysis. Methods. In this research, we present a simulation framework that
integrates the Swirl-Fire large-eddy simulation tool for wildfire predictions with the Vizier
optimization platform for automated run-time management of ensemble simulations and
large-scale batch processing. All simulations are executed on tensor-processing units to
enhance computational efficiency. Key results. A dataset of 117 simulations is created,
each with 1.35 billion mesh points. The simulations are compared to existing experimental
data and show good agreement in terms of fire rate of spread. Computations are done for
fire acceleration, mean rate of spread, and fireline intensity. Conclusions. Strong coupling
between these 2 parameters are observed for the fire spread and intermittency. A critical
Froude number that delineates fires from plume-driven to convection-driven is identified and
confirmed with literature observations. Implications. The ensemble simulation framework
is efficient in facilitating parametric wildfire studies.
View details
Knowledge Distillation with Perturbed Loss: From a Vanilla Teacher to a Proxy Teacher
Rongzhi Zhang
Chao Zhang
Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2024), ACM, pp. 4278 - 4289
Preview abstract
Knowledge distillation is a popular technique to transfer knowledge from a large teacher model to a small student model. Typically, the student learns to imitate the teacher by minimizing the KL divergence of its output distribution with the teacher's output distribution. In this work, we argue that such a learning objective is sub-optimal because there exists a discrepancy between the teacher's output distribution and the ground truth label distribution. Therefore, forcing the student to blindly imitate the unreliable teacher output distribution leads to inferior performance. To this end, we propose a novel knowledge distillation objective PTLoss by first representing the vanilla KL-based distillation loss function via a Maclaurin series and then perturbing the leading-order terms in this series. This perturbed loss implicitly transforms the original teacher into a proxy teacher with a distribution closer to the ground truth distribution. We establish the theoretical connection between this "distribution closeness'' and the student model generalizability, which enables us to select the PTLoss's perturbation coefficients in a principled way. Extensive experiments on six public benchmark datasets demonstrate the effectiveness of PTLoss with teachers of different scales.
View details
FEDAQT: ACCURATE QUANTIZED TRAINING WITH FEDERATED LEARNING
Renkun Ni
Oleg Rybakov
Phoenix Meadowlark
Tom Goldstein
Preview abstract
Federated learning has been widely used to train automatic speech recognition models, where the training procedure is decentralized to client devices to avoid data privacy concerns by keeping the training data locally. However, the limited computation resources on client devices prevent training with large models. Recently, quantization-aware training has shown the potential to train a quantized neural network with similar performance to the full-precision model while keeping the model size small and inference faster. However, these quantization methods will not save memory during training since they still keep the full-precision model. To address this issue, we propose a new quantization training framework for federated learning which saves the memory usage by training with quantized variables directly on local devices. We empirically show that our method can achieve comparable WER while only using 60% memory of the full-precision model.
View details
General Identifiability and Achievability for Causal Representation Learning
Burak Varici
Emre Acarturk
Ali Tajer
AISTATS 2024 (Oral), Oral Talk at NeurIPS Causal Representation Learning Workshop 2023. (2024)
Preview abstract
This paper focuses on causal representation learning (CRL) under a general nonparametric latent causal model and a general transformation model that maps the latent data to the observational data. It establishes identifiability and achievability results using two hard uncoupled interventions per node in the latent causal graph. Notably, one does
not know which pair of intervention environments have the same node intervened (hence,
uncoupled). For identifiability, the paper establishes that perfect recovery of the latent
causal model and variables is guaranteed under uncoupled interventions. For achievability,
an algorithm is designed that uses observational and interventional data and recovers
the latent causal model and variables with provable guarantees. This algorithm leverages
score variations across different environments to estimate the inverse of the transformer and,
subsequently, the latent variables. The analysis, additionally, recovers the identifiability
result for two hard coupled interventions, that is when metadata about the pair of environments that have the same node intervened is known. This paper also shows that when observational data is available, additional faithfulness assumptions that are adopted by the existing literature are unnecessary
View details
PriorBoost: An Adaptive Algorithm for Learning from Aggregate Responses
Adel Javanmard
Proceedings of the 41st International Conference on Machine Learning (2024), pp. 21410-21429
Preview abstract
This work studies algorithms for learning from aggregate responses. We focus on the construction of aggregation sets (called \emph{bags} in the literature) for event-level loss functions. We prove for linear regression and generalized linear models (GLMs) that the optimal bagging problem reduces to one-dimensional size-constrained $k$-means clustering. Further, we theoretically quantify the advantage of using curated bags over random bags. We propose the \texttt{PriorBoost} algorithm, which iteratively forms increasingly homogenous bags with respect to (unseen) individual responses to improve model quality. We also explore label differential privacy for aggregate learning, and provide extensive experiments that demonstrate that \PriorBoost regularly achieves optimal quality, in contrast to non-adaptive algorithms for aggregate learning.
View details
Unsupervised representation learning on high-dimensional clinical data improves genomic discovery and prediction
Babak Behsaz
Zachary Ryan Mccaw
Davin Hill
Robert Luben
Dongbing Lai
John Bates
Howard Yang
Tae-Hwi Schwantes-An
Yuchen Zhou
Anthony Khawaja
Andrew Carroll
Brian Hobbs
Michael Cho
Nature Genetics (2024)
Preview abstract
Although high-dimensional clinical data (HDCD) are increasingly available in biobank-scale datasets, their use for genetic discovery remains challenging. Here we introduce an unsupervised deep learning model, Representation Learning for Genetic Discovery on Low-Dimensional Embeddings (REGLE), for discovering associations between genetic variants and HDCD. REGLE leverages variational autoencoders to compute nonlinear disentangled embeddings of HDCD, which become the inputs to genome-wide association studies (GWAS). REGLE can uncover features not captured by existing expert-defined features and enables the creation of accurate disease-specific polygenic risk scores (PRSs) in datasets with very few labeled data. We apply REGLE to perform GWAS on respiratory and circulatory HDCD—spirograms measuring lung function and photoplethysmograms measuring blood volume changes. REGLE replicates known loci while identifying others not previously detected. REGLE are predictive of overall survival, and PRSs constructed from REGLE loci improve disease prediction across multiple biobanks. Overall, REGLE contain clinically relevant information beyond that captured by existing expert-defined features, leading to improved genetic discovery and disease prediction.
View details
Leveraging Function Space Aggregation for Federated Learning at Scale
Nikita Dhawan
Karolina Dziugaite
Transactions on Machine Learning Research (2024)
Preview abstract
The federated learning paradigm has motivated the development of methods for aggregating multiple client updates into a global server model, without sharing client data. Many federated learning algorithms, including the canonical Federated Averaging (FedAvg), take a direct (possibly weighted) average of the client parameter updates, motivated by results in distributed optimization. In this work, we adopt a function space perspective and propose a new algorithm, FedFish, that aggregates local approximations to the functions learned by clients, using an estimate based on their Fisher information. We evaluate FedFish on realistic, large-scale cross-device benchmarks. While the performance of FedAvg can suffer as client models drift further apart, we demonstrate that FedFish is more robust to longer local training. Our evaluation across several settings in image and language benchmarks shows that FedFish outperforms FedAvg as local training epochs increase. Further, FedFish results in global networks that are more amenable to efficient personalization via local fine-tuning on the same or shifted data distributions. For instance, federated pretraining on the C4 dataset, followed by few-shot personalization on Stack Overflow, results in a 7% improvement in next-token prediction by FedFish over FedAvg.
View details
Alignment of brain embeddings and artificial contextual embeddings in natural language points to common geometric patterns
Ariel Goldstein
Avigail Grinstein-Dabush
Haocheng Wang
Zhuoqiao Hong
Bobbi Aubrey
Samuel A. Nastase
Zaid Zada
Eric Ham
Harshvardhan Gazula
Eliav Buchnik
Werner Doyle
Sasha Devore
Patricia Dugan
Roi Reichart
Daniel Friedman
Orrin Devinsky
Adeen Flinker
Uri Hasson
Nature Communications (2024)
Preview abstract
Contextual embeddings, derived from deep language models (DLMs), provide
a continuous vectorial representation of language. This embedding space
differs fundamentally from the symbolic representations posited by traditional
psycholinguistics. We hypothesize that language areas in the human brain,
similar to DLMs, rely on a continuous embedding space to represent language.
To test this hypothesis, we densely record the neural activity patterns in the
inferior frontal gyrus (IFG) of three participants using dense intracranial arrays
while they listened to a 30-minute podcast. From these fine-grained spatiotemporal neural recordings, we derive a continuous vectorial representation
for each word (i.e., a brain embedding) in each patient. We demonstrate that
brain embeddings in the IFG and the DLM contextual embedding space have
common geometric patterns using stringent zero-shot mapping. The common
geometric patterns allow us to predict the brain embedding of a given left-out
word in IFG based solely on its geometrical relationship to other nonoverlapping words in the podcast. Furthermore, we show that contextual
embeddings better capture the geometry of IFG embeddings than static word
embeddings. The continuous brain embedding space exposes a vector-based
neural code for natural language processing in the human brain.
View details
Android Permissions: Evolution, Attacks, and Best Practices
IEEE Security and Privacy (2024) (to appear)
Preview abstract
In this article, we study the evolution of
Android permissions. We describe the rationale behind key changes in Android’s
permission model and disclose two permission-related security vulnerabilities
we discovered. Lastly, we provide developers actionable insights to proactively
address permission-related security and privacy risks during development.
View details
Expressing and Analyzing Quantum Algorithms with Qualtran
Charles Yuan
Anurudh Peduri
arXiv::2409.04643 (2024)
Preview abstract
Quantum computing's transition from theory to reality has spurred the need for novel software tools to manage the increasing complexity, sophistication, toil, and chance for error of quantum algorithm development. We present Qualtran, an open-source library for representing and analyzing quantum algorithms. Using carefully chosen abstractions and data structures, we can simulate and test algorithms, automatically generate information-rich diagrams, and tabulate resource requirements. Qualtran offers a \emph{standard library} of algorithmic building blocks that are essential for modern cost-minimizing compilations. Its capabilities are showcased through the re-analysis of key algorithms in Hamiltonian simulation, chemistry, and cryptography. The resulting architecture-independent resource counts can be forwarded to our implementation of cost models to estimate physical costs like wall-clock time and number of physical qubits assuming a surface-code architecture. Qualtran provides a foundation for explicit constructions and reproducible analysis, fostering greater collaboration within the quantum algorithm development community. We believe tools like Qualtran will accelerate progress in the field.
View details
Validation of a deep learning system for the detection of diabetic retinopathy in Indigenous Australians
Mark Chia
Fred Hersch
Pearse Keane
Angus Turner
British Journal of Ophthalmology, 108 (2024), pp. 268-273
Preview abstract
Background/aims: Deep learning systems (DLSs) for diabetic retinopathy (DR) detection show promising results but can underperform in racial and ethnic minority groups, therefore external validation within these populations is critical for health equity. This study evaluates the performance of a DLS for DR detection among Indigenous Australians, an understudied ethnic group who suffer disproportionately from DR-related blindness.
Methods: We performed a retrospective external validation study comparing the performance of a DLS against a retinal specialist for the detection of more-than-mild DR (mtmDR), vision-threatening DR (vtDR) and all-cause referable DR. The validation set consisted of 1682 consecutive, single-field, macula-centred retinal photographs from 864 patients with diabetes (mean age 54.9 years, 52.4% women) at an Indigenous primary care service in Perth, Australia. Three-person adjudication by a panel of specialists served as the reference standard.
Results: For mtmDR detection, sensitivity of the DLS was superior to the retina specialist (98.0% (95% CI, 96.5 to 99.4) vs 87.1% (95% CI, 83.6 to 90.6), McNemar’s test p<0.001) with a small reduction in specificity (95.1% (95% CI, 93.6 to 96.4) vs 97.0% (95% CI, 95.9 to 98.0), p=0.006). For vtDR, the DLS’s sensitivity was again superior to the human grader (96.2% (95% CI, 93.4 to 98.6) vs 84.4% (95% CI, 79.7 to 89.2), p<0.001) with a slight drop in specificity (95.8% (95% CI, 94.6 to 96.9) vs 97.8% (95% CI, 96.9 to 98.6), p=0.002). For all-cause referable DR, there was a substantial increase in sensitivity (93.7% (95% CI, 91.8 to 95.5) vs 74.4% (95% CI, 71.1 to 77.5), p<0.001) and a smaller reduction in specificity (91.7% (95% CI, 90.0 to 93.3) vs 96.3% (95% CI, 95.2 to 97.4), p<0.001).
Conclusion: The DLS showed improved sensitivity and similar specificity compared with a retina specialist for DR detection. This demonstrates its potential to support DR screening among Indigenous Australians, an underserved population with a high burden of diabetic eye disease.
View details
Shorts vs. Regular Videos on YouTube: A Comparative Analysis of User Engagement and Content Creation Trends
Caroline Violot
Tugrulcan Elmais
Mathias Humbert
ACM Web Science Conference 2024 (WEBSCI24) (2024)
Preview abstract
YouTube introduced the Shorts video format in 2021, allowing users to upload short videos that are prominently displayed on its website and app. Despite having such a large visual footprint, there are no studies to date that have looked at the impact Shorts introduction had on the production and consumption of content on YouTube.
This paper presents the first comparative analysis of YouTube Shorts versus regular videos with respect to user engagement (i.e., views, likes, and comments), content creation frequency and video categories. We collected a dataset containing information about 70k channels that posted at least one Short, and we analyzed the metadata of all the videos (9.9M Shorts and 6.9M regular videos) they uploaded between January 2021 and December 2022, spanning a two-year period including the introduction of Shorts. Our longitudinal analysis shows that content creators consistently increased the frequency of Shorts production over this period, especially for newly-created channels, which surpassed that of regular videos. We also observe that Shorts target mostly entertainment categories, while regular videos cover a wide variety of categories. In general, Shorts attract more views and likes per view than regular videos, but attract less comments per view. However, Shorts do not outperform regular videos in the education and political categories as much as they do in other categories.
Our study contributes to understanding social media dynamics, to quantifying the spread of short-form content, and to motivating future research on its impact on society.
View details
Creativity, Generative AI, and Software Development: A Research Agenda
Victoria Jackson
Bogdan Vasilescu
Daniel Russo
Paul Ralph
Maliheh Izadi
Rafael Prikladnicki
Anielle Lisboa
Andre van der Hoek
Preview abstract
Creativity has always been considered a major differentiator to separate the good from the great, and we believe the importance of creativity to software development will only increase as GenAI becomes embedded in developer tool-chains and working practices. This paper uses the McLuhan tetrad alongside scenarios of how GenAI may disrupt software development more broadly, to identify potential impacts GenAI may have on creativity within software development. The impacts are discussed along with a future research agenda comprising of six connected themes that consider how individual capabilities, team capabilities, the product, unintended consequences, society, and human aspects can be affected.
View details
