Decentralized Learning (DL) enables privacy-preserving collaboration among organizations or users to enhance the performance of local deep learning models. However, model aggregation becomes challenging when client data is heterogeneous, and identifying compatible collaborators without direct data exchange remains a pressing issue. In this paper, we investigate the effectiveness of various similarity metrics in DL for identifying peers for model merging, conducting an empirical analysis across multiple datasets with distribution shifts. Our research provides insights into the performance of these metrics, examining their role in facilitating effective collaboration. By exploring the strengths and limitations of these metrics, we contribute to the development of robust DL methods.

Decentralized Learning (DL) enables privacy-preserving collaboration among organizations or users to enhance the performance of local deep learning models. However, model aggregation becomes challenging when client data is heterogeneous, and identifying compatible collaborators without direct data exchange remains a pressing issue. In this paper, we investigate the effectiveness of various similarity metrics in DL for identifying peers for model merging, conducting an empirical analysis across multiple datasets with distribution shifts. Our research provides insights into the performance of these metrics, examining their role in facilitating effective collaboration. By exploring the strengths and limitations of these metrics, we contribute to the development of robust DL methods.

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. 

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)

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. 

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

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

Great environmental problems are facing us at an unprecedented level.One way of approaching these global challenges is by transitioning from a linear economy to a circular one. In a circular economy, product and material flows become circular, which can significantly improve resource efficiency for environmental sustainability. This can help with minimizing waste and pollution and aid in the regeneration of nature.Meanwhile, transitioning from linear business models to circular business models (CBMs) often leads to a number of financial risks for product companies, since they need to secure more capital in a stock of products that will be rented out over time. This leads to a slower, more volatile cash flow in the short term compared to linear direct sales of products.In this work, we address this problem by reducing the uncertainty of the future value of products. This can increase the willingness among financiers to be part of the development of new circular business models (CBMs). In particular, we study the predictability of online auction end prices using machine learning. The models are trained and evaluated on data collected from a Swedish online auction site.Our results show that deep learning is able to model the residual value of second-hand items on the market using user-uploaded text and images. Our hypothesis is that this technique will be useful to estimate the value of second-hand inventories and to help estimate the value of circular businesses, aiding in a transition from a linear to a circular economy. 

Data privacy is an increasingly important aspect of many real-world analytics tasks. Data sources that contain sensitive information may have immense potential which could be unlocked using the right privacy enhancing transformations, but current methods often fail to produce convincing output. Furthermore, finding the right balance between privacy and utility is often a tricky trade-off. In this work, we propose a novel approach for data privatization, which involves two steps: in the first step, it removes the sensitive information, and in the second step, it replaces this information with an independent random sample. Our method builds on adversarial representation learning which ensures strong privacy by training the model to fool an increasingly strong adversary. While previous methods only aim at obfuscating the sensitive information, we find that adding new random information in its place strengthens the provided privacy and provides better utility at any given level of privacy. The result is an approach that can provide stronger privatization on image data, and yet be preserving both the domain and the utility of the inputs, entirely independent of the downstream task. 

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.