Machine Learning for Musculoskeletal Modeling of Upper Extremity

We propose a novel machine learning (ML)-driven methodology to estimate biomechanical variables of interest traditionally obtained from upper-extremity musculoskeletal (MSK) modeling. MSK models facilitate personalized modeling, perform "what-if" analyses, and potentially enhance clinical decision-making. In certain settings, MSK models are driven by inertial motion capture (IMC) data. IMC systems are portable, user-friendly, and relatively affordable as well as provide additional biomechanical information. However, MSK models can be computationally expensive, often require extensive data, and can be prohibitively slow in making real-time predictions. Our ML method- involving a rigorous hyperparameters search-predicts kinematic and kinetic biomechanical information associated with human upper-extremity movements solely using IMC input data, thereby bypassing MSK models. The scaled cadaver-based MSK model was based on the Dutch Shoulder Model and the spine model implemented in the AnyBody Managed Model Repository. We employ neural networks (NNs), which are trained on IMC data obtained from five nondisabled subjects in subject- exposed (SE) settings (at least a trial from all subjects is used in training) and subject- naive (SN) settings (no information from test subjects is used in training). We compare the predictions of our ML model with that of an MSK model and find an excellent agreement in SE settings (average Pearson's r = 0.96, normalized RMSE (NRMSE) = 0.23) and strong correspondence in SN settings (average r = 0.89, NRMSE = 0.45). The linear model performed poorly for SN settings, which motivated a more complex ML model. Our findings suggest that an ML-based approach is highly viable for estimating upper-extremity biomechanical information solely from IMC data.

Open-ended Learning of Visual and Multi-modal Patterns

Jie Luo

A common trend in machine learning and pattern classification research is the exploitation of massive amounts of information in order to achieve an increase in performance. In particular, learning from huge collections of data obtained from the web, and using multiple features generated from different sources, have led to significantly boost of performance on problems that have been considered very hard for several years. In this thesis, we present two ways of using these information to build learning systems with robust performance and some degrees of autonomy. These ways are Cue Integration and Cue Exploitation, and constitute the two building blocks of this thesis. In the first block, we introduce several algorithms to answer the research question on how to integrate optimally multiple features. We first present a simple online learning framework which is a wrapper algorithm based on the high-level integration approach in the cue integration literature. It can be implemented with existing online learning algorithms, and preserves the theoretical properties of the algorithms being used. We then extend the Multiple Kernel Learning (MKL) framework, where each feature is converted into a kernel and the system learns the cue integration classifier by solving a joint optimization problem. To make the problem practical, We have designed two new regularization functions making it possible to optimize the problem efficiently. This results in the first online method for MKL. We also show two algorithms to solve the batch problem of MKL. Both of them have a guaranteed convergence rate. These approaches achieve state-of-the-art performance on several standard benchmark datasets, and are order of magnitude faster than other MKL solvers. In the second block, We present two examples on how to exploit information between different sources, in order to reduce the effort of labeling a large amount of training data. The first example is an algorithm to learn from partially annotated data, where each data point is tagged with a few possible labels. We show that it is possible to train a face classification system from data gathered from Internet, without any human labeling, but generating in an automatic way possible lists of labels from the captions of the images. Another example is under the transfer learning setting. The system uses existing models from potentially correlated tasks as experts, and transfers their outputs over the new incoming samples, of a new learning task where very few labeled data are available, to boost the performance.

Ecole polytechnique fédérale de Lausanne2011

Graph Representation Learning with Optimal Transport: Analysis and Applications

Effrosyni Simou

In several machine learning settings, the data of interest are well described by graphs. Examples include data pertaining to transportation networks or social networks. Further, biological data, such as proteins or molecules, lend themselves well to graph-structured descriptions. In such settings, it is desirable to design representation learning algorithms that can take into account the information captured by the underlying structure. This thesis focuses on providing new methods to ingrain geometrical information in end-to-end deep learning architectures for graphs through the use of elements from Optimal Transport theory.First, we consider the setting where the data can be described by a fixed graph. In this setting, each datapoint corresponds to a node of the graph and the edges among nodes signify their pairwise relations. We propose an autoencoder architecture that consists of a linear layer in the encoder and a novel Wasserstein barycentric layer at the decoder. Our proposed barycentric layer takes into account the underlying geometry through the diffusion distance of the graph and provides a way to obtain structure-aware, non-linear interpolations, which lead to directly interpretable node embeddings that are stable to perturbations of the graph structure. Further, the embeddings obtained with our proposed autoencoder achieve competitive or superior results compared to state-of-the-art methods in node classification tasks.Second, we consider the setting where the data consist of multiple graphs. In that setting, the graphs can be of varying size and, therefore, a global pooling operation is needed in order to obtain representations of fixed size and enable end-to-end learning with deep networks. We propose a global pooling operation that optimally preserves the statistical properties of the representations. In order to do so, we take into account the geometry of the representation space and introduce a global pooling layer that minimizes the Wasserstein distance between a graph representation and its pooled counterpart, of fixed size. This is achieved by performing a Wasserstein gradient flow with respect to the pooled representation. Our proposed method demonstrates promising results in the task of graph classification.Overall, in this thesis we provide new methods for incorporating geometrical information in end-to-end deep learning architectures for graph structured data. We believe that our proposals will contribute to the development of algorithms that learn meaningful representations and that take fully into account the geometry of the data under consideration.

EPFL2022

iPool--Information-Based Pooling in Hierarchical Graph Neural Networks

Pascal Frossard, Xing Gao, Chenglin Li

With the advent of data science, the analysis of network or graph data has become a very timely research problem. A variety of recent works have been proposed to generalize neural networks to graphs, either from a spectral graph theory or a spatial perspective. The majority of these works, however, focus on adapting the convolution operator to graph representation. At the same time, the pooling operator also plays an important role in distilling multiscale and hierarchical representations, but it has been mostly overlooked so far. In this article, we propose a parameter-free pooling operator, called iPool, that permits to retain the most informative features in arbitrary graphs. With the argument that informative nodes dominantly characterize graph signals, we propose a criterion to evaluate the amount of information of each node given its neighbors and theoretically demonstrate its relationship to neighborhood conditional entropy. This new criterion determines how nodes are selected and coarsened graphs are constructed in the pooling layer. The resulting hierarchical structure yields an effective isomorphism-invariant representation of networked data on arbitrary topologies. The proposed strategy achieves superior or competitive performance in graph classification on a collection of public graph benchmark data sets and superpixel-induced image graph data sets.