intertwined-hetero: Update abstract and summary

content/_index.md

@@ -137,7 +137,7 @@ sections:
         ### [Tackling Intertwined Data and Device Heterogeneities in Federated Learning with Unlimited Staleness](/publication/2023-intertwined-heterogeneity/) {id=intertwined-heterogeneity}
         AAAI 2025
         ![Intertwined Heterogeneity](2023-intertwined-heterogeneity/intertwined-heterogeneity-overview.png)
-        Federated Learning (FL) efficiency is influenced by intertwined data and device heterogeneities. Traditionally, these factors are treated separately, which becomes ineffective in addressing staleness issue due to asynchronous FL. We introduce a novel FL framework employing the gradient inversion technique to get estimations of clients' local training data from their uploaded stale model updates, and use these estimations to compute non-stale client model updates, which addresses both data quality and privacy concerns. Experiments on mainstream datasets reveal our approach enhances model accuracy by up to 20% and accelerates FL training by up to 35% over existing methods.
+        Federated Learning (FL) can be affected by data and device heterogeneities. Traditional schemes consider these heterogeneities as two separate and independent aspects, but this assumption is unrealistic in practical FL scenarios where these heterogeneities are intertwined. In these cases, traditional FL schemes are ineffective. We introduce a novel FL framework with the idea of estimating the distributions of clients' local training data from their uploaded stale model updates, and use these estimations to compute unstale client model updates. Experiments on comparison with existing FL strategies on mainstream datasets and models showed that our approach can improve the trained model accuracy by up to 25% and reduce the number of required training epochs by up to 35%.
         {{< hr-pittisl >}}
         ### [ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection](/publication/2023-elastictrainer/) {id=elastictrainer}
         MobiSys'23  

content/publication/2023-intertwined-heterogeneity/index.md

@@ -16,13 +16,13 @@ publishDate: '2023-09-25T00:00:11Z'
 publication_types: ['1']
 
 # Publication name and optional abbreviated publication name.
-publication: In *Proceedings of the 39th Annual Conference on Artificial Intelligence*
+publication: In *Proceedings of the 39th Annual Conference on Artificial Intelligence (AAAI 2025)*
 publication_short: In *AAAI 2025*
 
-abstract: Federated Learning (FL) can be affected by data and device heterogeneities, caused by clients' different local data distributions and latencies in uploading model updates (i.e., staleness). Traditional schemes consider these heterogeneities as two separate and independent aspects, but this assumption is unrealistic in practical FL scenarios where these heterogeneities are intertwined. In these cases, traditional FL schemes are ineffective, and a better approach is to convert a stale model update into a unstale one. In this paper, we present a new FL framework that ensures the accuracy and computational efficiency of this conversion, hence effectively tackling the intertwined heterogeneities that may cause unlimited staleness in model updates. Our basic idea is to estimate the distributions of clients' local training data from their uploaded stale model updates, and use these estimations to compute unstale client model updates. In this way, our approach does not require any auxiliary dataset nor the clients' local models to be fully trained, and does not incur any additional computation or communication overhead at client devices. We compared our approach with the existing FL strategies on mainstream datasets and models, and showed that our approach can improve the trained model accuracy by up to 25% and reduce the number of required training epochs by up to 35%. Source codes can be found at [this https URL](https://github.com/pittisl/FL-with-intertwined-heterogeneity).
+abstract: Federated Learning (FL) can be affected by data and device heterogeneities, caused by clients' different local data distributions and latencies in uploading model updates (i.e., staleness). Traditional schemes consider these heterogeneities as two separate and independent aspects, but this assumption is unrealistic in practical FL scenarios where these heterogeneities are intertwined. In these cases, traditional FL schemes are ineffective, and a better approach is to convert a stale model update into a unstale one. In this paper, we present a new FL framework that ensures the accuracy and computational efficiency of this conversion, hence effectively tackling the intertwined heterogeneities that may cause unlimited staleness in model updates. Our basic idea is to estimate the distributions of clients' local training data from their uploaded stale model updates, and use these estimations to compute unstale client model updates. In this way, our approach does not require any auxiliary dataset nor the clients' local models to be fully trained, and does not incur any additional computation or communication overhead at client devices. We compared our approach with the existing FL strategies on mainstream datasets and models, and showed that our approach can improve the trained model accuracy by up to 25% and reduce the number of required training epochs by up to 35%.
 
 # Summary. An optional shortened abstract.
-summary: Federated Learning (FL) efficiency is influenced by intertwined data and device heterogeneities. Traditionally, these factors are treated separately, which becomes ineffective in addressing staleness issue due to asynchronous FL. We introduce a novel FL framework employing the gradient inversion technique to get estimations of clients' local training data from their uploaded stale model updates, and use these estimations to compute non-stale client model updates, which addresses both data quality and privacy concerns. Experiments on mainstream datasets reveal our approach enhances model accuracy by up to 20% and accelerates FL training by up to 35% over existing methods.
+summary: Federated Learning (FL) can be affected by data and device heterogeneities. Traditional schemes consider these heterogeneities as two separate and independent aspects, but this assumption is unrealistic in practical FL scenarios where these heterogeneities are intertwined. In these cases, traditional FL schemes are ineffective. We introduce a novel FL framework with the idea of estimating the distributions of clients' local training data from their uploaded stale model updates, and use these estimations to compute unstale client model updates. Experiments on comparison with existing FL strategies on mainstream datasets and models showed that our approach can improve the trained model accuracy by up to 25% and reduce the number of required training epochs by up to 35%.
 
 tags:
   - 'on-device-ai'