Achieving high channel estimation accuracy and reducing hardware cost as well as power dissipation constitute substantial challenges in the design of massive multiple-input multiple-output (MIMO) systems. To resolve these difficulties, sophisticated pilot designs have been conceived for the family of energy-efficient hybrid analog-digital (HAD) beamforming architecture relying on adaptive-resolution analog-to-digital converters (RADCs). In this paper, we jointly optimize the pilot sequences, the number of RADC quantization bits and the hybrid receiver combiner in the uplink of multiuser massive MIMO systems. We solve the associated mean square error (MSE) minimization problem of channel estimation in the context of correlated Rayleigh fading channels subject to practical constraints. The associated mixed-integer problem is quite challenging due to the nonconvex nature of the objective function and of the constraints. By relying on advanced fractional programming (FP) techniques, we first recast the original problem into a more tractable yet equivalent form, which allows the decoupling of the fractional objective function. We then conceive a pair of novel algorithms for solving the resultant problems for codebook-based and codebook-free pilot schemes, respectively. To reduce the design complexity, we also propose a simplified algorithm for the codebook-based pilot scheme. Our simulation results confirm the superiority of the proposed algorithms over the relevant state-of-the-art benchmark schemes.
Bayesian learning with Gaussian processes demonstrates encouraging regression and classification performances in solving computer vision tasks. However, Bayesian methods on 3D manifold-valued vision data, such as meshes and point clouds, are seldom studied. One of the primary challenges is how to effectively and efficiently aggregate geometric features from the irregular inputs. In this paper, we propose a hierarchical Bayesian learning model to address this challenge. We initially introduce a kernel with the properties of geometry-awareness and intra-kernel convolution. This enables geometrically reasonable inferences on manifolds without using any specific hand-crafted feature descriptors. Then, we use a Gaussian process regression to organize the inputs and finally implement a hierarchical Bayesian network for the feature aggregation. Furthermore, we incorporate the feature learning of neural networks with the feature aggregation of Bayesian models to investigate the feasibility of jointly learning on manifolds. Experimental results not only show that our method outperforms existing Bayesian methods on manifolds but also demonstrate the prospect of coupling neural networks with Bayesian networks.
Biomarker-assisted diagnosis and intervention in Alzheimer's disease (AD) may be the key to prevention breakthroughs. One of the hallmarks of AD is the accumulation of tau plaques in the human brain. However, current methods to detect tau pathology are either invasive (lumbar puncture) or quite costly and not widely available (Tau PET). In our previous work, structural MRI-based hippocampal multivariate morphometry statistics (MMS) showed superior performance as an effective neurodegenerative biomarker for preclinical AD and Patch Analysis-based Surface Correntropy-induced Sparse coding and max-pooling (PASCS-MP) has excellent ability to generate low-dimensional representations with strong statistical power for brain amyloid prediction. In this work, we apply this framework together with ridge regression models to predict Tau deposition in Braak12 and Braak34 brain regions separately. We evaluate our framework on 925 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Each subject has one pair consisting of a PET image and MRI scan which were collected at about the same times. Experimental results suggest that the representations from our MMS and PASCS-MP have stronger predictive power and their predicted Braak12 and Braak34 are closer to the real values compared to the measures derived from other approaches such as hippocampal surface area and volume, and shape morphometry features based on spherical harmonics (SPHARM).
Cognitive decline due to Alzheimer's disease (AD) is closely associated with brain structure alterations captured by structural magnetic resonance imaging (sMRI). It supports the validity to develop sMRI-based univariate neurodegeneration biomarkers (UNB). However, existing UNB work either fails to model large group variances or does not capture AD dementia (ADD) induced changes. We propose a novel low-rank and sparse subspace decomposition method capable of stably quantifying the morphological changes induced by ADD. Specifically, we propose a numerically efficient rank minimization mechanism to extract group common structure and impose regularization constraints to encode the original 3D morphometry connectivity. Further, we generate regions-of-interest (ROI) with group difference study between common subspaces of $A\beta+$ AD and $A\beta-$ cognitively unimpaired (CU) groups. A univariate morphometry index (UMI) is constructed from these ROIs by summarizing individual morphological characteristics weighted by normalized difference between $A\beta+$ AD and $A\beta-$ CU groups. We use hippocampal surface radial distance feature to compute the UMIs and validate our work in the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. With hippocampal UMIs, the estimated minimum sample sizes needed to detect a 25$\%$ reduction in the mean annual change with 80$\%$ power and two-tailed $P=0.05$ are 116, 279 and 387 for the longitudinal $A\beta+$ AD, $A\beta+$ mild cognitive impairment (MCI) and $A\beta+$ CU groups, respectively. Additionally, for MCI patients, UMIs well correlate with hazard ratio of conversion to AD ($4.3$, $95\%$ CI=$2.3-8.2$) within 18 months. Our experimental results outperform traditional hippocampal volume measures and suggest the application of UMI as a potential UNB.
Applying network science approaches to investigate the functions and anatomy of the human brain is prevalent in modern medical imaging analysis. Due to the complex network topology, for an individual brain, mining a discriminative network representation from the multimodal brain networks is non-trivial. The recent success of deep learning techniques on graph-structured data suggests a new way to model the non-linear cross-modality relationship. However, current deep brain network methods either ignore the intrinsic graph topology or require a network basis shared within a group. To address these challenges, we propose a novel end-to-end deep graph representation learning (Deep Multimodal Brain Networks - DMBN) to fuse multimodal brain networks. Specifically, we decipher the cross-modality relationship through a graph encoding and decoding process. The higher-order network mappings from brain structural networks to functional networks are learned in the node domain. The learned network representation is a set of node features that are informative to induce brain saliency maps in a supervised manner. We test our framework in both synthetic and real image data. The experimental results show the superiority of the proposed method over some other state-of-the-art deep brain network models.
We propose to compute Wasserstein barycenters (WBs) by solving for Monge maps with variational principle. We discuss the metric properties of WBs and explore their connections, especially the connections of Monge WBs, to K-means clustering and co-clustering. We also discuss the feasibility of Monge WBs on unbalanced measures and spherical domains. We propose two new problems -- regularized K-means and Wasserstein barycenter compression. We demonstrate the use of VWBs in solving these clustering-related problems.
A large number of surface-based analyses on brain imaging data adopt some specific brain atlases to better assess structural and functional changes in one or more brain regions. In these analyses, it is necessary to obtain an anatomically correct surface parcellation scheme in an individual brain by referring to the given atlas. Traditional ways to accomplish this goal are through a designed surface-based registration or hand-crafted surface features, although both of them are time-consuming. A recent deep learning approach depends on a regular spherical parameterization of the mesh, which is computationally prohibitive in some cases and may also demand further post-processing to refine the network output. Therefore, an accurate and fully-automatic cortical surface parcellation scheme directly working on the original brain surfaces would be highly advantageous. In this study, we propose an end-to-end deep brain cortical parcellation network, called \textbf{DBPN}. Through intrinsic and extrinsic graph convolution kernels, DBPN dynamically deciphers neighborhood graph topology around each vertex and encodes the deciphered knowledge into node features. Eventually, a non-linear mapping between the node features and parcellation labels is constructed. Our model is a two-stage deep network which contains a coarse parcellation network with a U-shape structure and a refinement network to fine-tune the coarse results. We evaluate our model in a large public dataset and our work achieves superior performance than state-of-the-art baseline methods in both accuracy and efficiency
Lifelong learning, the problem of continual learning where tasks arrive in sequence, has been lately attracting more attention in the computer vision community. The aim of lifelong learning is to develop a system that can learn new tasks while maintaining the performance on the previously learned tasks. However, there are two obstacles for lifelong learning of deep neural networks: catastrophic forgetting and capacity limitation. To solve the above issues, inspired by the recent breakthroughs in automatically learning good neural network architectures, we develop a Multi-task based lifelong learning via nonexpansive AutoML framework termed Regularize, Expand and Compress (REC). REC is composed of three stages: 1) continually learns the sequential tasks without the learned tasks' data via a newly proposed multi-task weight consolidation (MWC) algorithm; 2) expands the network to help the lifelong learning with potentially improved model capability and performance by network-transformation based AutoML; 3) compresses the expanded model after learning every new task to maintain model efficiency and performance. The proposed MWC and REC algorithms achieve superior performance over other lifelong learning algorithms on four different datasets.
The increasing popularity and diversity of social media sites has encouraged more and more people to participate in multiple online social networks to enjoy their services. Each user may create a user identity to represent his or her unique public figure in every social network. User identity linkage across online social networks is an emerging task and has attracted increasing attention, which could potentially impact various domains such as recommendations and link predictions. The majority of existing work focuses on mining network proximity or user profile data for discovering user identity linkages. With the recent advancements in graph neural networks (GNNs), it provides great potential to advance user identity linkage since users are connected in social graphs, and learning latent factors of users and items is the key. However, predicting user identity linkages based on GNNs faces challenges. For example, the user social graphs encode both \textit{local} structure such as users' neighborhood signals, and \textit{global} structure with community properties. To address these challenges simultaneously, in this paper, we present a novel graph neural network framework ({\m}) for user identity linkage. In particular, we provide a principled approach to jointly capture local and global information in the user-user social graph and propose the framework {\m}, which jointly learning user representations for user identity linkage. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed framework.
State-of-the-art deep model compression methods exploit the low-rank approximation and sparsity pruning to remove redundant parameters from a learned hidden layer. However, they process each hidden layer individually while neglecting the common components across layers, and thus are not able to fully exploit the potential redundancy space for compression. To solve the above problem and enable further compression of a model, removing the cross-layer redundancy and mining the layer-wise inheritance knowledge is necessary. In this paper, we introduce a holistic model compression framework, namely MIning Cross-layer Inherent similarity Knowledge (MICIK), to fully excavate the potential redundancy space. The proposed MICIK framework simultaneously, (1) learns the common and unique weight components across deep neural network layers to increase compression rate; (2) preserves the inherent similarity knowledge of nearby layers and distant layers to minimize the accuracy loss and (3) can be complementary to other existing compression techniques such as knowledge distillation. Extensive experiments on large-scale convolutional neural networks demonstrate that MICIK is superior over state-of-the-art model compression approaches with 16X parameter reduction on VGG-16 and 6X on GoogLeNet, all without accuracy loss.