Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userKernel classification of connectomes based on earth movers distance between graph spectra
49
0
0.0
(
0
)
Added by
Yulia Dodonova
Publication date
2016
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
In this paper, we tackle a problem of predicting phenotypes from structural connectomes. We propose that normalized Laplacian spectra can capture structural properties of brain networks, and hence graph spectral distributions are useful for a task of connectome-based classification. We introduce a kernel that is based on earth movers distance (EMD) between spectral distributions of brain networks. We access performance of an SVM classifier with the proposed kernel for a task of classification of autism spectrum disorder versus typical development based on a publicly available dataset. Classification quality (area under the ROC-curve) obtained with the EMD-based kernel on spectral distributions is 0.71, which is higher than that based on simpler graph embedding methods.
rate research
Read More
Contour tracking in adverse environments is a challenging problem due to cluttered background, illumination variation, occlusion, and noise, among others. This paper presents a robust contour tracking method by contributing to some of the key issues involved, including (a) a region functional formulation and its optimization; (b) design of a robust and effective feature; and (c) development of an integrated tracking algorithm. First, we formulate a region functional based on robust Earth Movers distance (EMD) with kernel density for distribution modeling, and propose a two-phase method for its optimization. In the first phase, letting the candidate contour be fixed, we express EMD as the transportation problem and solve it by the simplex algorithm. Next, using the theory of shape derivative, we make a perturbation analysis of the contour around the best solution to the transportation problem. This leads to a partial differential equation (PDE) that governs the contour evolution. Second, we design a novel and effective feature for tracking applications. We propose a dimensionality reduction method by tensor decomposition, achieving a low-dimensional description of SIFT features called Tensor-SIFT for characterizing local image region properties. Applicable to both color and gray-level images, Tensor-SIFT is very distinctive, insensitive to illumination changes, and noise. Finally, we develop an integrated algorithm that combines various techniques of the simplex algorithm, narrow-band level set and fast marching algorithms. Particularly, we introduce an inter-frame initialization method and a stopping criterion for the termination of PDE iteration. Experiments in challenging image sequences show that the proposed work has promising performance.
In the context of single-label classification, despite the huge success of deep learning, the commonly used cross-entropy loss function ignores the intricate inter-class relationships that often exist in real-life tasks such as age classification. In this work, we propose to leverage these relationships between classes by training deep nets with the exact squared Earth Movers Distance (also known as Wasserstein distance) for single-label classification. The squared EMD loss uses the predicted probabilities of all classes and penalizes the miss-predictions according to a ground distance matrix that quantifies the dissimilarities between classes. We demonstrate that on datasets with strong inter-class relationships such as an ordering between classes, our exact squared EMD losses yield new state-of-the-art results. Furthermore, we propose a method to automatically learn this matrix using the CNNs own features during training. We show that our method can learn a ground distance matrix efficiently with no inter-class relationship priors and yield the same performance gain. Finally, we show that our method can be generalized to applications that lack strong inter-class relationships and still maintain state-of-the-art performance. Therefore, with limited computational overhead, one can always deploy the proposed loss function on any dataset over the conventional cross-entropy.
Sparse coding (Sc) has been studied very well as a powerful data representation method. It attempts to represent the feature vector of a data sample by reconstructing it as the sparse linear combination of some basic elements, and a $L_2$ norm distance function is usually used as the loss function for the reconstruction error. In this paper, we investigate using Sc as the representation method within multi-instance learning framework, where a sample is given as a bag of instances, and further represented as a histogram of the quantized instances. We argue that for the data type of histogram, using $L_2$ norm distance is not suitable, and propose to use the earth movers distance (EMD) instead of $L_2$ norm distance as a measure of the reconstruction error. By minimizing the EMD between the histogram of a sample and the its reconstruction from some basic histograms, a novel sparse coding method is developed, which is refereed as SC-EMD. We evaluate its performances as a histogram representation method in tow multi-instance learning problems --- abnormal image detection in wireless capsule endoscopy videos, and protein binding site retrieval. The encouraging results demonstrate the advantages of the new method over the traditional method using $L_2$ norm distance.
For graph classification tasks, many methods use a common strategy to aggregate information of vertex neighbors. Although this strategy provides an efficient means of extracting graph topological features, it brings excessive amounts of information that might greatly reduce its accuracy when dealing with large-scale neighborhoods. Learning graphs using paths or walks will not suffer from this difficulty, but many have low utilization of each path or walk, which might engender information loss and high computational costs. To solve this, we propose a graph kernel using a longest common subsequence (LCS kernel) to compute more comprehensive similarity between paths and walks, which resolves substructure isomorphism difficulties. We also combine it with optimal transport theory to extract more in-depth features of graphs. Furthermore, we propose an LCS metric space and apply an adjacent point merge operation to reduce its computational costs. Finally, we demonstrate that our proposed method outperforms many state-of-the-art graph kernel methods.
Graph distance metric learning serves as the foundation for many graph learning problems, e.g., graph clustering, graph classification and graph matching. Existing research works on graph distance metric (or graph kernels) learning fail to maintain the basic properties of such metrics, e.g., non-negative, identity of indiscernibles, symmetry and triangle inequality, respectively. In this paper, we will introduce a new graph neural network based distance metric learning approaches, namely GB-DISTANCE (GRAPH-BERT based Neural Distance). Solely based on the attention mechanism, GB-DISTANCE can learn graph instance representations effectively based on a pre-trained GRAPH-BERT model. Different from the existing supervised/unsupervised metrics, GB-DISTANCE can be learned effectively in a semi-supervised manner. In addition, GB-DISTANCE can also maintain the distance metric basic properties mentioned above. Extensive experiments have been done on several benchmark graph datasets, and the results demonstrate that GB-DISTANCE can out-perform the existing baseline methods, especially the recent graph neural network model based graph metrics, with a significant gap in computing the graph distance.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
