Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEdgeless-GNN: Unsupervised Inductive Edgeless Network Embedding
144
0
0.0
(
0
)
Added by
Won-Yong Shin
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
We study the problem of embedding edgeless nodes such as users who newly enter the underlying network, while using graph neural networks (GNNs) widely studied for effective representation learning of graphs thanks to its highly expressive capability via message passing. Our study is motivated by the fact that existing GNNs cannot be adopted for our problem since message passing to such edgeless nodes having no connections is impossible. To tackle this challenge, we propose Edgeless-GNN, a new framework that enables GNNs to generate node embeddings even for edgeless nodes through unsupervised inductive learning. Specifically, we start by constructing a $k$-nearest neighbor graph ($k$NNG) based on the similarity of node attributes to replace the GNNs computation graph defined by the neighborhood-based aggregation of each node. As our main contributions, the known network structure is used to train model parameters, while a new loss function is established using energy-based learning in such a way that our model learns the network structure. For the edgeless nodes, we inductively infer embeddings for the edgeless nodes by using edges via $k$NNG construction as a computation graph. By evaluating the performance of various downstream machine learning (ML) tasks, we empirically demonstrate that Edgeless-GNN consistently outperforms state-of-the-art methods of inductive network embedding. Moreover, our findings corroborate the effectiveness of Edgeless-GNN in judiciously combining the replaced computation graph with our newly designed loss. Our framework is GNN-model-agnostic; thus, GNN models can be appropriately chosen according to ones needs and ML tasks.
rate research
Read More
Considering the wide application of network embedding methods in graph data mining, inspired by the adversarial attack in deep learning, this paper proposes a Genetic Algorithm (GA) based Euclidean Distance Attack strategy (EDA) to attack the network embedding, so as to prevent certain structural information from being discovered. EDA focuses on disturbing the Euclidean distance between a pair of nodes in the embedding space as much as possible through minimal modifications of the network structure. Since a large number of downstream network algorithms, such as community detection and node classification, rely on the Euclidean distance between nodes to evaluate the similarity between them in the embedding space, EDA can be considered as a universal attack on a variety of network algorithms. Different from traditional supervised attack strategies, EDA does not need labeling information, and, in other words, is an unsupervised network embedding attack method.
A main challenge in mining network-based data is finding effective ways to represent or encode graph structures so that it can be efficiently exploited by machine learning algorithms. Several methods have focused in network representation at node/edge or substructure level. However, many real life challenges such as time-varying, multilayer, chemical compounds and brain networks involve analysis of a family of graphs instead of single one opening additional challenges in graph comparison and representation. Traditional approaches for learning representations relies on hand-crafting specialized heuristics to extract meaningful information about the graphs, e.g statistical properties, structural features, etc. as well as engineered graph distances to quantify dissimilarity between networks. In this work we provide an unsupervised approach to learn embedding representation for a collection of graphs so that it can be used in numerous graph mining tasks. By using an unsupervised neural network approach on input graphs, we aim to capture the underlying distribution of the data in order to discriminate between different class of networks. Our method is assessed empirically on synthetic and real life datasets and evaluated in three different tasks: graph clustering, visualization and classification. Results reveal that our method outperforms well known graph distances and graph-kernels in clustering and classification tasks, being highly efficient in runtime.
Dynamic Network Embedding (DNE) has recently attracted considerable attention due to the advantage of network embedding in various applications and the dynamic nature of many real-world networks. For dynamic networks, the degree of changes, i.e., defined as the averaged number of changed edges between consecutive snapshots spanning a dynamic network, could be very different in real-world scenarios. Although quite a few DNE methods have been proposed, it still remains unclear that whether and to what extent the existing DNE methods are robust to the degree of changes, which is however an important factor in both academic research and industrial applications. In this work, we investigate the robustness issue of DNE methods w.r.t. the degree of changes for the first time and accordingly, propose a robust DNE method. Specifically, the proposed method follows the notion of ensembles where the base learner adopts an incremental Skip-Gram neural embedding approach. To further boost the performance, a novel strategy is proposed to enhance the diversity among base learners at each timestep by capturing different levels of local-global topology. Extensive experiments demonstrate the benefits of special designs in the proposed method, and the superior performance of the proposed method compared to state-of-the-art methods. The comparative study also reveals the robustness issue of some DNE methods. The source code is available at https://github.com/houchengbin/SG-EDNE
Topological materials bear gapped excitations in bulk yet protected gapless excitations at boundaries. Magnetoplasmons (MPs), as high-frequency density excitations of two-dimensional electron gas (2DEG) in a perpendicular magnetic field, embody a prototype of band topology for bosons. The time-reversal-breaking magnetic field opens a topological gap for bulk MPs up to the cyclotron frequency; topologically-protected edge magnetoplasmons (EMPs) bridge the bulk gap and propagate unidirectionally along systems boundaries. However, all the EMPs known to date adhere to physical edges where the electron density terminates abruptly. This restriction has made device application extremely difficult. Here we demonstrate a new class of topological edge plasmons -- domain-boundary magnetoplasmons (DBMPs), within a uniform edgeless 2DEG. Such DBMPs arise at the domain boundaries of an engineered sign-changing magnetic field and are protected by the difference of gap Chern numbers (+/-1) across the magnetic domains. They propagate unidirectionally along the domain boundaries and are immune to domain defects. Moreover, they exhibit wide tunability in the microwave frequency range under an applied magnetic field or gate voltage. Our study opens a new direction to realize high-speed reconfigurable topological devices.
To cope with the harsh environment foreseen at the high luminosity conditions of HL- LHC, the ATLAS pixel detector has to be upgraded to be fully efficient with a good granularity, a maximized geometrical acceptance and an high read out rate. LPNHE, FBK and INFN are involved in the development of thin and edgeless planar pixel sensors in which the insensitive area at the border of the sensor is minimized thanks to the active edge technology. In this paper we report on two productions, a first one consisting of 200 {mu}m thick n-on-p sensors with active edge, a second one composed of 100 and 130 {mu}m thick n-on-p sensors. Those sensors have been tested on beam, both at CERN-SPS and at DESY and their performance before and after irradiation will be presented.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
