scholarly journals C3MM: Clique-Closure based Hyperlink Prediction

2020 ◽  
Author(s):  
Govind Sharma ◽  
Prasanna Patil ◽  
M. Narasimha Murty
Keyword(s):  
Link Prediction ◽  
Recent Literature ◽  
State Of The Art ◽  
Hypothesis Test ◽  
Higher Order ◽  
The State ◽  
Complex Structures ◽  
Prediction Problem ◽  
Order Relations

Usual networks lossily (if not incorrectly) represent higher-order relations, i.e. those between multiple entities instead of a pair. This calls for complex structures such as hypergraphs to be used instead. Akin to the link prediction problem in graphs, we deal with hyperlink (higher-order link) prediction in hypergraphs. With a handful of solutions in the literature that seem to have merely scratched the surface, we provide improvements for the same. Motivated by observations in recent literature, we first formulate a "clique-closure" hypothesis (viz., hyperlinks are more likely to be formed from near-cliques rather than from non-cliques), test it on real hypergraphs, and then exploit it for our very problem. In the process, we generalize hyperlink prediction on two fronts: (1) from small-sized to arbitrary-sized hyperlinks, and (2) from a couple of domains to a handful. We perform experiments (both the hypothesis-test as well as the hyperlink prediction) on multiple real datasets, report results, and provide both quantitative and qualitative arguments favoring better performances w.r.t. the state-of-the-art.

scholarly journals Relational Gating for ''What If'' Reasoning

2021 ◽  
Author(s):  
Chen Zheng ◽  
Parisa Kordjamshidi
Keyword(s):  
State Of The Art ◽  
Higher Order ◽  
The State ◽  
Order Relations ◽  
Reasoning Problem ◽  
Gating Network

This paper addresses the challenge of learning to do procedural reasoning over text to answer "What if..." questions. We propose a novel relational gating network that learns to filter the key entities and relationships and learns contextual and cross representations of both procedure and question for finding the answer. Our relational gating network contains an entity gating module, relation gating module, and contextual interaction module. These modules help in solving the "What if..." reasoning problem. We show that modeling pairwise relationships helps to capture higher-order relations and find the line of reasoning for causes and effects in the procedural descriptions. Our proposed approach achieves the state-of-the-art results on the WIQA dataset.

scholarly journals A Graph-based Evolutionary Algorithm for Automated Machine Learning

2020 ◽  
Author(s):  
Fei Qi ◽  
Zhaohui Xia ◽  
Gaoyang Tang ◽  
Hang Yang ◽  
Yu Song ◽  
...  
Keyword(s):  
Machine Learning ◽  
Evolutionary Algorithm ◽  
Parameter Optimization ◽  
State Of The Art ◽  
The State ◽  
Complex Structures ◽  
Architecture Evolution ◽  
Automated Machine Learning ◽  
Art Performance

As an emerging field, Automated Machine Learning (AutoML) aims to reduce or eliminate manual operations that require expertise in machine learning. In this paper, a graph-based architecture is employed to represent flexible combinations of ML models, which provides a large searching space compared to tree-based and stacking-based architectures. Based on this, an evolutionary algorithm is proposed to search for the best architecture, where the mutation and heredity operators are the key for architecture evolution. With Bayesian hyper-parameter optimization, the proposed approach can automate the workflow of machine learning. On the PMLB dataset, the proposed approach shows the state-of-the-art performance compared with TPOT, Autostacker, and auto-sklearn. Some of the optimized models are with complex structures which are difficult to obtain in manual design.

scholarly journals Link prediction in social networks: the state-of-the-art

2014 ◽  
Vol 58 (1) ◽  
pp. 1-38 ◽  
Author(s):  
Peng Wang ◽  
BaoWen Xu ◽  
YuRong Wu ◽  
XiaoYu Zhou
Keyword(s):  
Social Networks ◽  
Link Prediction ◽  
State Of The Art ◽  
The State

scholarly journals Building a Real-Time 2D Lidar Using Deep Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Nadim Arubai ◽  
Omar Hamdoun ◽  
Assef Jafar
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Obstacle Avoidance ◽  
Tilt Angle ◽  
State Of The Art ◽  
The State ◽  
Prediction Problem ◽  
Learning Methods ◽  
Depth Prediction ◽  
Avoidance Problem

Applying deep learning methods, this paper addresses depth prediction problem resulting from single monocular images. A vector of distances is predicted instead of a whole image matrix. A vector-only prediction decreases training overhead and prediction periods and requires less resources (memory, CPU). We propose a module which is more time efficient than the state-of-the-art modules ResNet, VGG, FCRN, and DORN. We enhanced the network results by training it on depth vectors from other levels (we get a new level by changing the Lidar tilt angle). The predicted results give a vector of distances around the robot, which is sufficient for the obstacle avoidance problem and many other applications.

scholarly journals PR_22_0642603_Chipscale_NLO

2022 ◽  
Author(s):  
Shayan Mookherjee
Keyword(s):  
Signal Processing ◽  
Nonlinear Optics ◽  
Quantum Optics ◽  
Conversion Efficiency ◽  
Optical Signal Processing ◽  
State Of The Art ◽  
Optical Signal ◽  
Higher Order ◽  
The State ◽  
Disorder Effects

Multi-microresonator photonic circuits can improve the conversion efficiency of nonlinear optics, realize higher-order, implement programmable filters, and other advances in optical signal processing. However, such structures are challenging to realize in practice. Through a deeper understanding of disorder effects in photonics, we have greatly advanced the state-of-the-art in CROW structures and their applications in linear, nonlinear and quantum optics.

scholarly journals Learning Non-Uniform Hypergraph for Multi-Object Tracking

2019 ◽  
Vol 33 ◽  
pp. 8981-8988 ◽  
Author(s):  
Longyin Wen ◽  
Dawei Du ◽  
Shengkun Li ◽  
Xiao Bian ◽  
Siwei Lyu
Keyword(s):  
Support Vector Machine ◽  
Object Tracking ◽  
State Of The Art ◽  
Higher Order ◽  
The State ◽  
Support Vector ◽  
Support Vector Machine Algorithm ◽  
Uniform Hypergraph ◽  
Detection Scheme ◽  
Structural Support

The majority of Multi-Object Tracking (MOT) algorithms based on the tracking-by-detection scheme do not use higher order dependencies among objects or tracklets, which makes them less effective in handling complex scenarios. In this work, we present a new near-online MOT algorithm based on non-uniform hypergraph, which can model different degrees of dependencies among tracklets in a unified objective. The nodes in the hypergraph correspond to the tracklets and the hyperedges with different degrees encode various kinds of dependencies among them. Specifically, instead of setting the weights of hyperedges with different degrees empirically, they are learned automatically using the structural support vector machine algorithm (SSVM). Several experiments are carried out on various challenging datasets (i.e., PETS09, ParkingLot sequence, SubwayFace, and MOT16 benchmark), to demonstrate that our method achieves favorable performance against the state-of-the-art MOT methods.

scholarly journals Point-of-interest recommendation in location-based social networks

2021 ◽  
Author(s):  
Alireza Pourali
Keyword(s):  
Similarity Search ◽  
Link Prediction ◽  
State Of The Art ◽  
Graph Representation ◽  
Prediction Problem ◽  
Related Information ◽  
Point Of Interest ◽  
Factorization Model ◽  
Feature Based ◽  
Location Based Social Networks

The focus of point-of-interest recommendation techniques is to suggest a venue to a given user that would match the users’ interests and is likely to be adopted by the user. Given the multitude of the available venues and the sparsity of user check-ins, the problem of recommending venues has shown to be a difficult task. Existing literature has already explored various types of features such as geographical distribution, social structure and temporal behavioral patterns to make a recommendation. In this thesis, we show how a comprehensive set of user and venue related information can be methodically incorporated into a heterogeneous graph representation based on which the problem of venue recommendation can be efficiently formulated as an instance of the heterogeneous link prediction problem on the graph and we propose a new set of features derived based on the neural embeddings of venues and users. We additionally show how the neural embeddings for users and venues can be jointly learnt based on the prior check-in sequence of users and then be used to define a set of new features. We have also used a new proposed heterogeneous graph similarity search framework to find similarity between users and venues using our graph. These features are integrated into a feature-based matrix factorization model. Our experiments show that the features defined over the user and venue embeddings are effective for venue recommendation and outperform existing state of the art methods.

scholarly journals Point-of-interest recommendation in location-based social networks

2021 ◽  
Author(s):  
Alireza Pourali
Keyword(s):  
Similarity Search ◽  
Link Prediction ◽  
State Of The Art ◽  
Graph Representation ◽  
Prediction Problem ◽  
Related Information ◽  
Point Of Interest ◽  
Factorization Model ◽  
Feature Based ◽  
Location Based Social Networks

The focus of point-of-interest recommendation techniques is to suggest a venue to a given user that would match the users’ interests and is likely to be adopted by the user. Given the multitude of the available venues and the sparsity of user check-ins, the problem of recommending venues has shown to be a difficult task. Existing literature has already explored various types of features such as geographical distribution, social structure and temporal behavioral patterns to make a recommendation. In this thesis, we show how a comprehensive set of user and venue related information can be methodically incorporated into a heterogeneous graph representation based on which the problem of venue recommendation can be efficiently formulated as an instance of the heterogeneous link prediction problem on the graph and we propose a new set of features derived based on the neural embeddings of venues and users. We additionally show how the neural embeddings for users and venues can be jointly learnt based on the prior check-in sequence of users and then be used to define a set of new features. We have also used a new proposed heterogeneous graph similarity search framework to find similarity between users and venues using our graph. These features are integrated into a feature-based matrix factorization model. Our experiments show that the features defined over the user and venue embeddings are effective for venue recommendation and outperform existing state of the art methods.

scholarly journals RWNE: A Scalable Random-Walk based Network Embedding Framework with Personalized Higher-order Proximity Preserved

2021 ◽  
Vol 71 ◽  
pp. 237-263
Author(s):  
Jianxin Li ◽  
Cheng Ji ◽  
Hao Peng ◽  
Yu He ◽  
Yangqiu Song ◽  
...  
Keyword(s):  
Random Walk ◽  
Random Walks ◽  
Real World ◽  
State Of The Art ◽  
Higher Order ◽  
The State ◽  
Random Walk With Restart ◽  
Network Embedding ◽  
Network Proximity ◽  
Embedding Methods

Higher-order proximity preserved network embedding has attracted increasing attention. In particular, due to the superior scalability, random-walk-based network embedding has also been well developed, which could efficiently explore higher-order neighborhoods via multi-hop random walks. However, despite the success of current random-walk-based methods, most of them are usually not expressive enough to preserve the personalized higher-order proximity and lack a straightforward objective to theoretically articulate what and how network proximity is preserved. In this paper, to address the above issues, we present a general scalable random-walk-based network embedding framework, in which random walk is explicitly incorporated into a sound objective designed theoretically to preserve arbitrary higher-order proximity. Further, we introduce the random walk with restart process into the framework to naturally and effectively achieve personalized-weighted preservation of proximities of different orders. We conduct extensive experiments on several real-world networks and demonstrate that our proposed method consistently and substantially outperforms the state-of-the-art network embedding methods.

scholarly journals A Multi-Scale Approach for Graph Link Prediction

2020 ◽  
Vol 34 (04) ◽  
pp. 3308-3315 ◽  
Author(s):  
Lei Cai ◽  
Shuiwang Ji
Keyword(s):  
Neural Networks ◽  
Link Prediction ◽  
Prediction Models ◽  
State Of The Art ◽  
The State ◽  
Graph Structure ◽  
Scale Invariant ◽  
Multi Scale ◽  
Heuristic Learning ◽  
Graph Neural Networks

Deep models can be made scale-invariant when trained with multi-scale information. Images can be easily made multi-scale, given their grid-like structures. Extending this to generic graphs poses major challenges. For example, in link prediction tasks, inputs are represented as graphs consisting of nodes and edges. Currently, the state-of-the-art model for link prediction uses supervised heuristic learning, which learns graph structure features centered on two target nodes. It then learns graph neural networks to predict the existence of links based on graph structure features. Thus, the performance of link prediction models highly depends on graph structure features. In this work, we propose a novel node aggregation method that can transform the enclosing subgraph into different scales and preserve the relationship between two target nodes for link prediction. A theory for analyzing the information loss during the re-scaling procedure is also provided. Graphs in different scales can provide scale-invariant information, which enables graph neural networks to learn invariant features and improve link prediction performance. Our experimental results on 14 datasets from different areas demonstrate that our proposed method outperforms the state-of-the-art methods by employing multi-scale graphs without additional parameters.

Sign in / Sign up

Export Citation Format

Share Document