Frugal Decentralized Learning | EPFL Graph Search

Machine learning is currently shifting from a centralized paradigm to decentralized ones where machine learning models are trained collaboratively. In fully decentralized learning algorithms, data remains where it was produced, models are trained locally and only model parameters are exchanged among participating entities along an arbitrary network topology and aggregated over time until convergence. Not only this limits the cost of exchanging data but also exploits the growing capabilities of users' devices while mitigating privacy and confidentiality concerns. Such systems are significantly challenged by a potential high-level of heterogeneity both at the system level as participants may have differing capabilities of (e.g., computing power, memory and network connectivity) as well as data heterogeneity (a.k.a non- IIDness). The adoption of fully decentralized learning systems requires designing frugal systems that limit communication, energy and yet ensure convergences. Several avenues are promising from adapting the network topologies to compensate for data heterogeneity to exploiting the high levels of redundancy, both in data and computations, of ML algorithms to limit data and model sharing in such systems.

Intelligent Clustering for Graph Visualization

Lionel Jérémie Martin

More and more areas use graphs for the representation of their data because it gives a connection-oriented perspective. Unfortunately, datasets are constantly growing in size, while devices have increasingly smaller screens (tablets, smartphones, etc). In order to reduce the quantity of elements displayed on screen, several techniques of information reduction can be used. Among them is graph clustering, which aggregates the elements of the original graph into clustered nodes and edges - thereby leading to a smaller graph. In this report, we present a tool for the interactive exploration and analysis of large clustered graphs. The tool empowers users to control the granularity of graphs either by direct interaction (collapsing/expanding clusters) or via a slider that automatically computes a clustered graph of the desired size. In a next step, we explore the use of learning algorithms to capture graph exploration preferences based on a history of user interactions.The learned parameters are then used to modify the action of the slider in view of mimicking the natural interaction/exploration behavior of the user.

2013

Multi-Centroid Hyperdimensional Computing Approach for Epileptic Seizure Detection

David Atienza Alonso, Una Pale, Tomas Teijeiro Campo

Long-term monitoring of patients with epilepsy presents a challenging problem from the engineering perspective of real-time detection and wearable devices design. It requires new solutions that allow continuous unobstructed monitoring and reliable detection and prediction of seizures. A high variability in the electroencephalogram (EEG) patterns exists among people, brain states, and time instances during seizures, but also during non-seizure periods. This makes epileptic seizure detection very challenging, especially if data is grouped under only seizure (ictal) and non-seizure (inter-ictal) labels. Hyperdimensional (HD) computing, a novel machine learning approach, comes in as a promising tool. However, it has certain limitations when the data shows a high intra-class variability. Therefore, in this work, we propose a novel semi-supervised learning approach based on a multi-centroid HD computing. The multi-centroid approach allows to have several prototype vectors representing seizure and non-seizure states, which leads to significantly improved performance when compared to a simple single-centroid HD model. Further, real-life data imbalance poses an additional challenge and the performance reported on balanced subsets of data is likely to be overestimated. Thus, we test our multi-centroid approach with three different dataset balancing scenarios, showing that performance improvement is higher for the less balanced dataset. More specifically, up to 14% improvement is achieved on an unbalanced test set with 10 times more non-seizure than seizure data. At the same time, the total number of sub-classes is not significantly increased compared to the balanced dataset. Thus, the proposed multi-centroid approach can be an important element in achieving a high performance of epilepsy detection with real-life data balance or during online learning, where seizures are infrequent.

2022

Multi-Centroid Hyperdimensional Computing Approach for Epileptic Seizure Detection

David Atienza Alonso, Una Pale, Tomas Teijeiro Campo

2022