| 1. |
- Ekblom, Ebba, et al.
(författare)
-
EFFGAN: Ensembles of fine-tuned federated GANs
- 2022
-
Konferensbidrag (refereegranskat)abstract
- Decentralized machine learning tackles the problemof learning useful models when data is distributed amongseveral clients. The most prevalent decentralized setting todayis federated learning (FL), where a central server orchestratesthe learning among clients. In this work, we contribute to therelatively understudied sub-field of generative modelling in theFL framework.We study the task of how to train generative adversarial net-works (GANs) when training data is heterogeneously distributed(non-iid) over clients and cannot be shared. Our objective isto train a generator that is able to sample from the collectivedata distribution centrally, while the client data never leaves theclients and user privacy is respected. We show using standardbenchmark image datasets that existing approaches fail in thissetting, experiencing so-called client drift when the local numberof epochs becomes to large and local parameters drift too faraway in parameter space. To tackle this challenge, we proposea novel approach namedEFFGAN: Ensembles of fine-tunedfederated GANs. Being an ensemble of local expert generators, EFFGAN is able to learn the data distribution over all clientsand mitigate client drift. It is able to train with a large numberof local epochs, making it more communication efficient thanprevious works
|
|
| 2. |
- Ericsson, David, et al.
(författare)
-
Adversarial representation learning for private speech generation
- 2020
-
Konferensbidrag (refereegranskat)abstract
- As more data is collected in various settingsacross organizations, companies, and countries,there has been an increase in the demand of userprivacy. Developing privacy preserving methodsfor data analytics is thus an important area of research. In this work we present a model basedon generative adversarial networks (GANs) thatlearns to obfuscate specific sensitive attributes inspeech data. We train a model that learns to hidesensitive information in the data, while preservingthe meaning in the utterance. The model is trainedin two steps: first to filter sensitive informationin the spectrogram domain, and then to generatenew and private information independent of thefiltered one. The model is based on a U-Net CNNthat takes mel-spectrograms as input. A MelGANis used to invert the spectrograms back to rawaudio waveforms. We show that it is possible tohide sensitive information such as gender by generating new data, trained adversarially to maintainutility and realism.
|
|
| 3. |
- Fallahi, Sara, 1985-, et al.
(författare)
-
Financing solutions for circular business models : Exploring the role of business ecosystems and artificial intelligence
- 2023
-
Ingår i: Business Strategy and the Environment. - : John Wiley and Sons Ltd. - 0964-4733 .- 1099-0836. ; 32:6
-
Tidskriftsartikel (refereegranskat)abstract
- The circular economy promotes a transition away from linear modes of production and consumption to systems with circular material flows that can significantly improve resource productivity. However, transforming linear business models to circular business models posits a number of financial consequences for product companies as they need to secure more capital in a stock of products that will be rented out over time and therefore will encounter a slower, more volatile cash flow in the short term compared to linear direct sales of products. This paper discusses the role of financial actors in circular business ecosystems and alternative financing solutions when moving from product-dominant business models to Product-as-a-Service (PaaS) or function-based business models. Furthermore, the paper demonstrates a solution where state-of-the-art artificial intelligence (AI) modeling can be incorporated for financial risk assessment. We provide an open implementation and a thorough empirical evaluation of an AI-model, which learns to predict residual value of stocks of used items. Furthermore, the paper highlights solutions, managerial implications, and potentials for financing circular business models, argues the importance of different forms of data in future business ecosystems, and offers recommendations for how AI can help mitigate some of the challenges businesses face as they transition to circular business models. © 2022 The Authors.
|
|
| 4. |
- Isaksson, Martin, et al.
(författare)
-
Adaptive Expert Models for Personalization in Federated Learning
- 2022
-
Ingår i: International Workshop on Trustworthy Federated Learningin Conjunction with IJCAI 2022 (FL-IJCAI'22).
-
Konferensbidrag (refereegranskat)abstract
- Federated Learning (FL) is a promising framework for distributed learning whendata is private and sensitive. However, the state-of-the-art solutions in thisframework are not optimal when data is heterogeneous and non-Independent andIdentically Distributed (non-IID). We propose a practical and robust approachto personalization in FL that adjusts to heterogeneous and non-IID data bybalancing exploration and exploitation of several global models. To achieve ouraim of personalization, we use a Mixture of Experts (MoE) that learns to groupclients that are similar to each other, while using the global models moreefficiently. We show that our approach achieves an accuracy up to 29.78 % andup to 4.38 % better compared to a local model in a pathological non-IIDsetting, even though we tune our approach in the IID setting.
|
|
| 5. |
- Isaksson, Martin, et al.
(författare)
-
Adaptive Expert Models for Federated Learning
- 2023
-
Ingår i: <em>Lecture Notes in Computer Science </em>Volume 13448 Pages 1 - 16 2023. - Cham : Springer Science and Business Media Deutschland GmbH. - 9783031289958 ; 13448 LNAI, s. 1-16
-
Konferensbidrag (refereegranskat)abstract
- Federated Learning (FL) is a promising framework for distributed learning when data is private and sensitive. However, the state-of-the-art solutions in this framework are not optimal when data is heterogeneous and non-IID. We propose a practical and robust approach to personalization in FL that adjusts to heterogeneous and non-IID data by balancing exploration and exploitation of several global models. To achieve our aim of personalization, we use a Mixture of Experts (MoE) that learns to group clients that are similar to each other, while using the global models more efficiently. We show that our approach achieves an accuracy up to 29.78% better than the state-of-the-art and up to 4.38% better compared to a local model in a pathological non-IID setting, even though we tune our approach in the IID setting. © 2023, The Author(s)
|
|
| 6. |
- Listo Zec, Edvin, et al.
(författare)
-
Decentralized Adaptive Clustering of Deep Nets is Beneficial for Client Collaboration
- 2023
-
Ingår i: FL 2022. - Cham : Springer Nature. ; , s. 59-71
-
Konferensbidrag (refereegranskat)abstract
- We study the problem of training personalized deep learning models in a decentralized peer-to-peer setting, focusing on the setting where data distributions differ between the clients and where different clients have different local learning tasks. We study both covariate and label shift, and our contribution is an algorithm which for each client finds beneficial collaborations based on a similarity estimate for the local task. Our method does not rely on hyperparameters which are hard to estimate, such as the number of client clusters, but rather continuously adapts to the network topology using soft cluster assignment based on a novel adaptive gossip algorithm. We test the proposed method in various settings where data is not independent and identically distributed among the clients. The experimental evaluation shows that the proposed method performs better than previous state-of-the-art algorithms for this problem setting, and handles situations well where previous methods fail.
|
|
| 7. |
- Listo Zec, Edvin, et al.
(författare)
-
Statistical Sensor Modelling for Autonomous Driving Using Autoregressive Input-Output HMMs
- 2018
-
Ingår i: 21st International Conference on Intelligent Transportation Systems, {ITSC} 2018. - : IEEE. - 2153-0017. - 9781728103211
-
Konferensbidrag (refereegranskat)abstract
- Advanced driver assistance systems (ADAS) are standard features in many vehicles today and they have been proven to significantly increase the traffic safety. This paved way for development of autonomous driving (AD). To enable this, the vehicles are equipped with many sensors such as cameras and radars in order to scan the surrounding environment. The sensor outputs are used to implement decision and control modules. Verification of AD is a challenging task and requires collecting data from at least hundreds of millions of autonomously driven miles. We are therefore interested in virtual verification methods that simulate interesting and relevant situations, so that many scenarios can be tested in parallel. Realistic simulations require accurate sensor models, and in this paper we propose a probabilistic model based on the hidden Markov model (HMM) for modelling the sequential data produced by the sensors used in ADAS and AD. Moreover, we propose an efficient way to estimate parameters that scales well to big data sets. The results show that extending the HMM to use autoregression and input dependent transition probabilities is important in order to model the sensor characteristics and substantially improves the performance.
|
|
| 8. |
- Zec, Edvin Listo, et al.
(författare)
-
Decentralized adaptive clustering of deep nets is beneficial for client collaboration
- 2022
-
Konferensbidrag (refereegranskat)abstract
- We study the problem of training personalized deep learning models in a decentralized peer-to-peer setting, focusing on the setting where data distributions differ between the clients and where different clients have different local learning tasks. We study both covariate and label shift, and our contribution is an algorithm which for each client finds beneficial collaborations based on a similarity estimate for the local task. Our method does not rely on hyperparameters which are hard to estimate, such as the number of client clusters, but rather continuously adapts to the network topology using soft cluster assignment based on a novel adaptive gossip algorithm. We test the proposed method in various settings where data is not independent and identically distributed among the clients. The experimental evaluation shows that the proposed method performs better than previous state-of-the-art algorithms for this problem setting, and handles situations well where previous methods fail
|
|
| 9. |
- Zec, Edvin Listo, et al.
(författare)
-
Efficient Node Selection in Private Personalized Decentralized Learning
- 2024
-
Konferensbidrag (refereegranskat)abstract
- Personalized decentralized learning is a promising paradigm for distributed learning, enabling each node to train a local model on its own data and collaborate with other nodes to improve without sharing any data. However, this approach poses significant privacy risks, as nodes may inadvertently disclose sensitive information about their data or preferences through their collaboration choices. In this paper, we propose Private Personalized Decentralized Learning (PPDL), a novel approach that combines secure aggregation and correlated adversarial multi-armed bandit optimization to protect node privacy while facilitating efficient node selection. By leveraging dependencies between different arms, represented by potential collaborators, we demonstrate that PPDL can effectively identify suitable collaborators solely based on aggregated models. Additionally, we show that PPDL surpasses previous non-private methods in model performance on standard benchmarks under label and covariate shift scenarios.
|
|
| 10. |
|
|
