Dec 2026· IEEE Transactions on Knowledge and Data Engineering· Vol 38, pp. 8152-8166· 0 citations· 49 references
TL;DR
This paper first establishes inter-shard relationships via a personalized aggregation mechanism, which significantly alleviates the model accuracy degradation caused by disjoint sharding and non-IID data, while still ensuring confined unlearning overhead.
Abstract
Recent privacy regulations increasingly emphasize the right to erase the impact of individual participants in Federated Learning (FL), a distributed learning paradigm in which multiple clients collaboratively train a global model without sharing their local data. Existing approaches tackle this Federated Unlearning (FU) problem primarily by partitioning client data into disjoint shards, thereby confining the impact of revoked clients. However, the fundamental challenges of FL, such as non-IID data distributions and stochastic participation during training, remain significant obstacles to achieving both efficient and effective FU. To overcome these limitations, this paper presents a novel adaptive data partitioning framework. We first establish inter-shard relationships via a personalized aggregation mechanism, which significantly alleviates the model accuracy degradation caused by disjoint sharding and non-IID data, while still ensuring confined unlearning overhead. Additionally, we propose a dynamic client-to-shard reassignment strategy. It accelerates FU by balancing the distribution of unlearning workloads, especially when processing successive revocations. Furthermore, clients within each shard are partitioned into fine-grained slices, enabling prioritized participation scheduling and adaptive slice sizing to enhance overall performance. Evaluations conducted in both simulated and real-world FL scenarios demonstrate that our framework runs 4× faster with an improvement of 6× in accuracy, compared to state-of-the-art competitors.
The results indicate that software engineering work practices are chosen opportunistically, adapted and configured to provide value under the constrains imposed by the startup context.
Nicolò Paternoster, Carmine Giardino, M. Unterkalmsteiner et al.· Information and Software Tec...· 394 citations· ⚡54
This state-of-practice investigation was performed using a literature review followed by a multiple-case study approach and presents how inconsistency between managerial strategies and execution can lead to failure by means of a behavioral framework.
Carmine Giardino, Xiaofeng Wang, P. Abrahamsson· International Conference on...· 175 citations· ⚡19
This study conducts a case survey study based on the secondary data of the major pivots happened in 49 software startups, and demonstrates that customer need pivot is the most common among all pivot types.
Sohaib Shahid Bajwa, Xiaofeng Wang, Anh Nguyen-Duc et al.· Empirical Software Engineeri...· 127 citations· ⚡15
It is found that roles of MVPs in startups were not fully aware by entrepreneurs, and entrepreneurs should consider a systematic approach to fully explore the value of MVP, as a multiple facet product (MFP).
Anh Nguyen-Duc, P. Abrahamsson· International Conference on...· 93 citations· ⚡9
It is found that what perceived as biggest challenges by software startups do vary across different life cycle stages, even though its significance decreases when the learning focuses of the startups move from problem to solution and their products mature.
Xiaofeng Wang, Henry Edison, Sohaib Shahid Bajwa et al.· International Conference on...· 62 citations· ⚡6
A comprehensive overview of how enhanced sampling methods are reshaping the field, with a particular focus on the data-driven construction of collective variables, is provided.
Kai Zhu, Enrico Trizio, Jintu Zhang et al.· Chemical Reviews· 58 citations
Related blog posts
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 9, 2026
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.