skip to main content

Search for: All records

Creators/Authors contains: "Li, T."

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Free, publicly-accessible full text available May 18, 2022
  2. In this work, we explore the unique challenges---and opportunities---of unsupervised federated learning (FL). We develop and analyze a one-shot federated clustering scheme, k-FED, based on the widely-used Lloyd's method for k-means clustering. In contrast to many supervised problems, we show that the issue of statistical heterogeneity in federated networks can in fact benefit our analysis. We analyse k-FED under a center separation assumption and compare it to the best known requirements of its centralized counterpart. Our analysis shows that in heterogeneous regimes where the number of clusters per device (k') is smaller than the total number of clusters over themore »network k, ($k' \le \sqrt{k}$), we can use heterogeneity to our advantage---significantly weakening the cluster separation requirements for k-FED. From a practical viewpoint, k-FED also has many desirable properties: it requires only round of communication, can run asynchronously, and can handle partial participation or node/network failures. We motivate our analysis with experiments on common FL benchmarks, and highlight the practical utility of one-shot clustering through use-cases in personalized FL and device sampling.« less
  3. Fairness and robustness are two important concerns for federated learning systems. In this work, we identify that robustness to data and model poisoning attacks and fairness, measured as the uniformity of performance across devices, are competing constraints in statistically heterogeneous networks. To address these constraints, we propose employing a simple, general framework for personalized federated learning, Ditto, and develop a scalable solver for it. Theoretically, we analyze the ability of Ditto to achieve fairness and robustness simultaneously on a class of linear problems. Empirically, across a suite of federated datasets, we show that Ditto not only achieves competitive performance relativemore »to recent personalization methods, but also enables more accurate, robust, and fair models relative to state-of-the-art fair or robust baselines.« less
  4. Tuning hyperparameters is a crucial but arduous part of the machine learning pipeline. Hyperparameter optimization is even more challenging in federated learning, where models are learned over a distributed network of heterogeneous devices; here, the need to keep data on device and perform local training makes it difficult to efficiently train and evaluate configurations. In this work, we investigate the problem of federated hyperparameter tuning. We first identify key challenges and show how standard approaches may be adapted to form baselines for the federated setting. Then, by making a novel connection to the neural architecture search technique of weight-sharing, wemore »introduce a new method, FedEx, to accelerate federated hyperparameter tuning that is applicable to widely-used federated optimization methods such as FedAvg and recent variants. Theoretically, we show that a FedEx variant correctly tunes the on-device learning rate in the setting of online convex optimization across devices. Empirically, we show that FedEx can outperform natural baselines for federated hyperparameter tuning by several percentage points on the Shakespeare, FEMNIST, and CIFAR-10 benchmarks, obtaining higher accuracy using the same training budget.« less
  5. Free, publicly-accessible full text available October 1, 2022
  6. This experimental research studies consumer preferences for local food accompanied by various label definitions. 374 adult participants made purchase decisions for local oysters characterized by multiple definitions of the term local. Results show consumers are less willing to pay for local oysters when local is defined as harvested within 400 miles than they are for oysters harvested within 100 miles or 25 miles. Willingness to pay (WTP) also increases when local is defined as being harvested in a watershed from the same state of the purchase location rather than in an adjacent state. Interestingly, the highest WTP is when nomore »definition of local is provided.« less
  7. While rare-earth borides represent a class of important materials in modern industries, there are few fundamental researches on their electronic structures and physicochemical properties. Recently we have performed combined experimental and theoretical studies on rare-earth boron clusters and their cluster-assembled complexes, revealing a series of rare-earth inverse sandwich clusters with fascinating electronic structures and chemical bonding patterns. In this overview article, we summarize recent progresses in this area and provide a perspective view on the future development of rare-earth boride clusters. Understanding the electronic structures of these clusters helps to design materials of f-element (lanthanide and actinide) borides with criticalmore »physiochemical properties.« less
  8. Free, publicly-accessible full text available April 1, 2022