Mingqing Chen
Research Areas
Authored Publications
Google Publications
Other Publications
Sort By
Preview abstract
Personalization of speech models on mobile devices (on-device personalization) is an active area of research, but more often than not, mobile devices have more text-only data than paired audio-text data. We explore training a personalized language model on text-only data, used during inference to improve speech recognition performance for that user. We experiment on a user-clustered LibriSpeech corpus, supplemented with personalized text-only data for each user from Project Gutenberg. We release this User-Specific LibriSpeech (UserLibri) dataset to aid future personalization research. LibriSpeech audio-transcript pairs are grouped into 55 users from the test-clean dataset and 52 users from test-other. We are able to lower the average word error rate per user across both sets in streaming and nonstreaming models, including an improvement of 2.5 for the harder set of test-other users when streaming.
View details
Scaling Language Model Size in Cross-Device Federated Learning
FL4NLP@ACL2022 (2022) (to appear)
Preview abstract
Most studies in cross-device federated learning focus on small models, due to the server-client communication and on-device computation bottlenecks. In this work, we leverage various techniques for mitigating these bottlenecks to train larger language models in cross-device federated learning. With systematic applications of partial model training, quantization, efficient transfer learning, and communication-efficient optimizers, we are able to train a 21M parameter Transformer that achieves the same perplexity as that of a similarly sized LSTM with ~10x smaller client-to-server communication cost and 11% lower perplexity than smaller LSTMs commonly studied in literature.
View details
Online Model Compression for Federated Learning with Large Models
Tien-Ju Yang
Giovanni Motta
(2022)
Preview abstract
This paper addresses the challenges of training large neural network models under federated learning settings: high on-device memory usage and communication cost. The proposed Online Model Compression (OMC) provides a framework that stores model parameters in a compressed format and decompresses them only when needed. We use quantization as the compression method in this paper and propose three methods, (1) using per-variable transformation, (2) weight matrices only quantization, and (3) partial parameter quantization, to minimize the impact on model accuracy. According to our experiments on two recent neural networks for speech recognition and two different datasets, OMC can reduce memory usage and communication cost of model parameters by up to 59% while attaining comparable accuracy and training speed when compared with full-precision training.
View details
Preview abstract
Almost none of the 2,000+ languages spoken in Africa have widely available automatic speech recognition systems, and the required data is also only available for a few languages. We have experimented with two techniques which may provide pathways to large vocabulary speech recognition for African languages: multilingual modeling and self-supervised learning. We gathered available open source data and collected data for 15 languages, and trained experimental models using these techniques. Our results show that pooling the small amounts of data available in multilingual end-to-end models, and pre-training on unsupervised data can help improve speech recognition quality for many African languages.
View details
Capitalization Normalization for Language Modeling with an Accurate and Efficient Hierarchical RNN Model
You-Chi Cheng
IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022, {IEEE}, pp. 6097-6101
Preview abstract
Capitalization normalization (truecasing) is the task of restoring the correct case (uppercase or lowercase) of noisy text. We propose a fast, accurate and compact two-level hierarchical word-and-character-based recurrent neural network model. We use the truecaser to normalize user-generated text in a Federated Learning framework for language modeling. A case-aware language model trained on this normalized text achieves the same perplexity as a model trained on text with gold capitalization. In a real user A/B experiment, we demonstrate that the improvement translates to reduced prediction error rates in a virtual keyboard application. Similarly, in an ASR language model fusion experiment, we show reduction in uppercase character error rate and word error rate.
View details
Diurnal or Nocturnal? Federated Learning of Multi-branch Networks from Periodically Shifting Distributions
Chen Zhu
Jakub Konečný
Tom Goldstein
International Conference on Learning Representations (2022) (to appear)
Preview abstract
Federated learning has been applied to train machine learning models from decentralized client data on mobile devices in practice. The population of the large scale clients are observed to have periodically shifting distributions, which can cause instability in training and degrade the final model performance. In this paper, instead of adopting the block-cyclic distribution shifts in previous papers, we model the population distribution to be a mixture distribution gradually changing between daytime subpopulation and nighttime subpopulation. We verified this intuitive modification better matches the training observation in practical federated learning systems.
We propose multi-branch networks to handle the domain differences in subpopulations, and exploit a federated Expectation-Maximization (EM) algorithm with temporal priors to select branches for each client to handle the distribution shift. Experiments for image classification on EMNIST and CIFAR datasets, and next word prediction on the Stack Overflow dataset show that the proposed algorithm can effectively mitigate the impact of the distribution shift and significantly improve the final model performance.
View details
Preview abstract
Truecasing is the task of restoring the correct case (uppercase or lowercase) of noisy text generated either by an automatic system for speech recognition or machine translation or by humans. It improves the performance of downstream NLP tasks such as named entity recognition and language modeling. We propose a fast, accurate and compact two-level hierarchical word-and-character-based recurrent neural network model, the first of its kind for this problem. Using sequence distillation, we also address the problem of truecasing while ignoring token positions in the sentence, i.e. in a position-invariant manner.
View details
Preview abstract
Federated learning is used for decentralized training of machine learning models on millions of edge mobile devices. This is challenging because these devices often have limited communication bandwidth, and local computation resources. We exploit partially trainable neural networks, which freeze a portion of the model parameters during the entire training process, to reduce the communication cost with little implications on model performance. Through extensive experiments, we empirically show that Federated learning of Partially Trainable neural networks (FedPT) can result in good communication-accuracy trade-offs, with up to $46\times$ reduction in communication cost, at a small accuracy cost. The proposed FedPT can be particularly interesting for pushing the limitations of overparameterization for on-device learning.
View details
Preview abstract
In distributed learning settings such as federated learning, the training algorithm can be potentially biased towards different clients. Mohri et al. (2019) proposed a domain-agnostic learning algorithm, where the model is optimized for any target distribution formed by a mixture of the client distributions in order to overcome this bias. They further proposed an algorithm for the cross-silo federated learning setting, where the number of clients is small. We consider this problem in the cross-device setting, where the number of clients is much larger. We propose a communication-efficient distributed algorithm called Agnostic Federated Averaging (or AgnosticFedAvg) to minimize the domain-agnostic objective proposed in (Mohri et al., 2019), which is amenable to other private mechanisms such as secure aggregation. We highlight two types of naturally occurring domains in federated learning and argue that AgnosticFedAvg performs well on both. To demonstrate the practical effectiveness of AgnosticFedAvg, we report positive results for large-scale language modeling tasks in both simulation and live experiments, where the latter involves training language models for Spanish virtual keyboard for millions of user devices.
View details
Generative Models for Effective ML on Private, Decentralized Datasets
8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020, OpenReview.net
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
Federated Learning of N-gram Language Models
Adeline Wong
The SIGNLL Conference on Computational Natural Language Learning (2019)
Preview abstract
We propose algorithms to train production-quality n-gram language models using federated learning. Federated learning is a machine learning technique to train global models to be used on portable devices such as smart phones, without the users' data ever leaving their devices. This is especially relevant for applications handling privacy-sensitive data, such as virtual keyboards. While the principles of federated learning are fairly generic, its methodology assumes that the underlying models are neural networks. However, virtual keyboards are typically powered by n-gram language models, mostly for latency reasons.
We propose to train a recurrent neural network language model using the decentralized "FederatedAveraging" algorithm directly on training and to approximating this federated model server-side with an n-gram model that can be deployed to devices for fast inference.
Our technical contributions include novel ways of handling large vocabularies, algorithms to correct capitalization errors in user data, and efficient finite state transducer algorithms to convert word language models to word-piece language models and vice versa.
The n-gram language models trained with federated learning are compared to n-grams trained with traditional server-based algorithms using A/B tests on tens of millions of users of a virtual keyboard.
Results are presented for two languages, American English and Brazilian Portuguese. This work demonstrates that high-quality n-gram language models can be trained directly on client mobile devices without sensitive training data ever leaving the device.
View details
Preview abstract
We demonstrate that a character-level LSTM neural network is able to learn
out-of-vocabulary (OOV) words for the purpose of expanding the vocabulary of
a virtual keyboard for smartphones.
We train such a model using a distributed, on-device learning framework called federated learning.
High-frequency words can then be sampled from the generative model
by drawing from the joint posterior directly.
We study the feasibility of the approach in three different settings:
(1) using stochastic gradient descent, on an anonymized dataset of snippets of user content;
(2) using simulated federated learning, on a publicly available non-IID per-user dataset from a popular social networking website;
(3) using federated learning, on data hosted on user mobile devices.
The model is shown to achieve good recall and precision when compared to ground-truth OOV words in settings (1) and (2).
With (3) we demonstrate the practicality of this approach by showing that we can learn meaningful OOV words without exporting sensitive user data to servers.
View details
No Results Found
