Filters








3,304 Hits in 5.6 sec

A Bi-Level Framework for Learning to Solve Combinatorial Optimization on Graphs [article]

Runzhong Wang, Zhigang Hua, Gan Liu, Jiayi Zhang, Junchi Yan, Feng Qi, Shuang Yang, Jun Zhou, Xiaokang Yang
<span title="2021-10-25">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose a hybrid approach to combine the best of the two worlds, in which a bi-level framework is developed with an upper-level learning method to optimize the graph (e.g. add, delete  ...  or modify edges in a graph), fused with a lower-level heuristic algorithm solving on the optimized graph.  ...  We would also like to thank Chang Liu, Jia Yan and Runsheng Gan for their valuable discussions when we were working on this paper.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.04927v3">arXiv:2106.04927v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/k5x3zr4pxze6jh622cem7paikq">fatcat:k5x3zr4pxze6jh622cem7paikq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211106184522/https://arxiv.org/pdf/2106.04927v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/de/76/de7634ec3412712d216f01c98c75372839631825.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.04927v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Curriculum learning for multilevel budgeted combinatorial problems [article]

Adel Nabli, Margarida Carvalho
<span title="2020-10-26">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Learning heuristics for combinatorial optimization problems through graph neural networks have recently shown promising results on some classic NP-hard problems.  ...  We report results close to optimality on graphs up to 100 nodes and a 185 × speedup on average compared to the quickest exact solver known for the Multilevel Critical Node problem, a max-min-max trilevel  ...  Science for Combinatorial Game Theory, and the Natural Sciences and Engineering Research Council of Canada through the discovery grant 2019-04557.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.03151v2">arXiv:2007.03151v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3kzvzfe5jjhq7gxlonkdvucwb4">fatcat:3kzvzfe5jjhq7gxlonkdvucwb4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201030202249/https://arxiv.org/pdf/2007.03151v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a0/61/a0613f960502b7cf59d6854d9fa58fa770c4dcd4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.03151v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

PDP: A General Neural Framework for Learning Constraint Satisfaction Solvers [article]

Saeed Amizadeh, Sergiy Matusevych, Markus Weimer
<span title="2019-03-05">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Our experimental results demonstrate the effectiveness of our framework for SAT solving compared to both neural and the state-of-the-art baselines.  ...  Our framework is based on the idea of propagation, decimation and prediction (and hence the name PDP) in graphical models, and can be trained directly toward solving CSP in a fully unsupervised manner  ...  The PDP Framework In order to develop a neural framework for learning to solve CSPs, first we need a suitable design pattern that would allow solving CSPs via neural networks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1903.01969v1">arXiv:1903.01969v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/drgloat33rdffk3vwmpj6nv3fy">fatcat:drgloat33rdffk3vwmpj6nv3fy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200904222032/https://arxiv.org/pdf/1903.01969v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/8b/f6/8bf690ace672c438c3a87d416bd5e37aaa204835.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1903.01969v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learning-Based Approaches for Graph Problems: A Survey [article]

Kai Siong Yow, Siqiang Luo
<span title="2022-04-17">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this survey, we provide a systematic review mainly on classic graph problems in which learning-based approaches have been proposed in addressing the problems.  ...  Recent studies have employed learning-based frameworks such as machine learning techniques in solving these problems, given that they are useful in discovering new patterns in structured data that can  ...  [35] proposed a framework to solve the TSP by extending the neural combinatorial optimization framework.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.01057v2">arXiv:2204.01057v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6oinpd56njcu5ait43327r6ege">fatcat:6oinpd56njcu5ait43327r6ege</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220422095108/https://arxiv.org/pdf/2204.01057v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/25/4a/254abac8ec2e31d979f84a4e31793f19eb0ac7b9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.01057v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Recent Progress on Graph Partitioning Problems Using Evolutionary Computation [article]

Hye-Jin Kim, Yong-Hyuk Kim
<span title="2018-05-04">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The graph partitioning problem (GPP) is a representative combinatorial optimization problem which is NP-hard. Currently, various approaches to solve GPP have been introduced.  ...  There has not been any survey on the research applying EC to GPP since 2011. In this survey, we introduce various attempts to apply EC to GPP made in the recent seven years.  ...  The k-way graph partitioning problem is a problem to partition a graph into k subsets. When k = 2, it is referred as graph bisection or bi-partitioning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.01623v1">arXiv:1805.01623v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/x6ww35oxpvfrpdy3m4c2znk6n4">fatcat:x6ww35oxpvfrpdy3m4c2znk6n4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200907121801/https://arxiv.org/pdf/1805.01623v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6a/ec/6aec08be707c1112f0cfcb475167ff53d3f6aee3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.01623v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Neural Combinatorial Optimization with Reinforcement Learning [article]

Irwan Bello, Hieu Pham, Quoc V. Le, Mohammad Norouzi, Samy Bengio
<span title="2017-01-12">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper presents a framework to tackle combinatorial optimization problems using neural networks and reinforcement learning.  ...  We compare learning the network parameters on a set of training graphs against learning them on individual test graphs.  ...  ACKNOWLEDGMENTS The authors would like to thank Vincent Furnon, Oriol Vinyals, Barret Zoph, Lukasz Kaiser, Mustafa Ispir and the Google Brain team for insightful comments and discussion.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1611.09940v3">arXiv:1611.09940v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jc4t6xphjjhebgutggbgxs4noi">fatcat:jc4t6xphjjhebgutggbgxs4noi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191013190027/https://arxiv.org/pdf/1611.09940v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/42/76/4276b0f54583aca1e74a1c822a7ad7c22d3a41ba.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1611.09940v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Meta-Learning with Graph Neural Networks: Methods and Applications [article]

Debmalya Mandal, Sourav Medya, Brian Uzzi, Charu Aggarwal
<span title="2021-11-06">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Meta-learning has been an important framework to address the lack of samples in machine learning, and in recent years, researchers have started to apply meta-learning to GNNs.  ...  Graph Neural Networks (GNNs), a generalization of deep neural networks on graph data have been widely used in various domains, ranging from drug discovery to recommender systems.  ...  The application of meta-learning to GNNs is a growing and exciting field and we believe many graph problems will benefit immensely from the combination of the two approaches.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.00137v3">arXiv:2103.00137v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/odsdbw34hjazxg43slwvfz7nki">fatcat:odsdbw34hjazxg43slwvfz7nki</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211121162613/https://arxiv.org/pdf/2103.00137v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/85/c2/85c2a6d8f48db5e85d5555b1e2ec2be03b6c3f90.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.00137v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A grouping hyper-heuristic framework based on linear linkage encoding for graph coloring

Anas Elhag, Ender Ozcan
<span title="">2013</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/45jrmsqavfgmrmzqqhlmio3xue" style="color: black;">2013 13th UK Workshop on Computational Intelligence (UKCI)</a> </i> &nbsp;
Selection hyper-heuristics based on iterative search frameworks are high level general problem solving methodologies which operate on a set of low level heuristics to improve an initially generated solution  ...  Grouping problems are a class of combinatorial optimization problems in which the task is to search for the best partition of a set of objects into a collection of mutually disjoint subsets while satisfying  ...  Our aim is to provide a single selection hyper-heuristic framework for all grouping problems. We tested our framework on instances from the graph coloring problem domain, in this study. II.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/ukci.2013.6651323">doi:10.1109/ukci.2013.6651323</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ukci/ElhagO13.html">dblp:conf/ukci/ElhagO13</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6ymtbrltazegrcglbvpw3q5t2m">fatcat:6ymtbrltazegrcglbvpw3q5t2m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809133903/http://www.cs.nott.ac.uk/~pszeo/docs/publications/ukci2013_grouping.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ec/4c/ec4c79aa6a5ebe55e6b4ea57990b99ea9d6a7189.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/ukci.2013.6651323"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A Survey for Solving Mixed Integer Programming via Machine Learning [article]

Jiayi Zhang and Chang Liu and Junchi Yan and Xijun Li and Hui-Ling Zhen and Mingxuan Yuan
<span title="2022-03-06">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Like other CO problems, the human-designed heuristic algorithms for MIP rely on good initial solutions and cost a lot of computational resources.  ...  Finally, we propose the outlook for learning-based MIP solvers, direction towards more combinatorial optimization problems beyond MIP, and also the mutual embrace of traditional solvers and machine learning  ...  ., 2021] is focused on bi-level tailored approaches that exploit MIP techniques to solve bilevel optimization problems.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.02878v1">arXiv:2203.02878v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wiezy5ilird3fgbf3qdjzj4wmu">fatcat:wiezy5ilird3fgbf3qdjzj4wmu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220310233358/https://arxiv.org/pdf/2203.02878v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/72/3f/723f1b9377e25148001322718fd1a4a498efe28e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.02878v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Automating Crystal-Structure Phase Mapping: Combining Deep Learning with Constraint Reasoning [article]

Di Chen, Yiwei Bai, Sebastian Ament, Wenting Zhao, Dan Guevarra, Lan Zhou, Bart Selman, R. Bruce van Dover, John M. Gregoire, Carla P. Gomes
<span title="2021-08-21">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
DRNets combine deep learning with constraint reasoning for incorporating scientific prior knowledge and consequently require only a modest amount of (unlabeled) data.  ...  DRNets surpass previous approaches on crystal-structure phase mapping, unraveling the Bi-Cu-V oxide phase diagram, and aiding the discovery of solar-fuels materials.  ...  The authors also thank Junwen Bai for assistance with running the IAFD baseline, Aniketa Shinde for photoelectrochemistry experiments, and Rich Berstein for assistance with figure generation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.09523v1">arXiv:2108.09523v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sed2voog2nhm3iz4yp77xyqksm">fatcat:sed2voog2nhm3iz4yp77xyqksm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210829163709/https://arxiv.org/pdf/2108.09523v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/fe/76/fe76b663d4c920e019f184972dcf75a2d713005b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.09523v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Sequential Evaluation and Generation Framework for Combinatorial Recommender System [article]

Fan Wang, Xiaomin Fang, Lihang Liu, Yaxue Chen, Jiucheng Tao, Zhiming Peng, Cihang Jin, Hao Tian
<span title="2019-06-23">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Toward solving this problem, we propose the Evaluation-Generation framework.  ...  On the other hand, generation policies based on heuristic searching or reinforcement learning are devised to generate potential high-quality sequences, from which the evaluation model select one to expose  ...  We propose the Evaluator-Generator framework to solve the combinatorial optimization problem.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.00245v3">arXiv:1902.00245v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xj2mp4w7q5h7zcgfe5t6z44fla">fatcat:xj2mp4w7q5h7zcgfe5t6z44fla</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200913202508/https://arxiv.org/pdf/1902.00245v2.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6b/59/6b59fd15c21cff37edd19689aa84c6c77b19ca1d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.00245v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Emergency response facility location in transportation networks: A literature review

Yang Liu, Yun Yuan, Jieyi Shen, Wei Gao
<span title="">2021</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/7lumuzrhqfbvphhul5yv6htipq" style="color: black;">Journal of Traffic and Transportation Engineering (English ed. Online)</a> </i> &nbsp;
This review is aimed to provide a combined framework for emergency facility location in transportation networks.  ...  Emergency facility location Transportation networks Travel time Machine learning a b s t r a c t Emergency response activity relies on transportation networks.  ...  Machine learning-based paradigm is a new area for combinatorial optimization (Deng et al., 2020) .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.jtte.2021.03.001">doi:10.1016/j.jtte.2021.03.001</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nyyzzu5hpvgglmzaa7st7upfn4">fatcat:nyyzzu5hpvgglmzaa7st7upfn4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210528183345/https://pdf.sciencedirectassets.com/312331/1-s2.0-S2095756421X00037/1-s2.0-S2095756421000222/main.pdf?X-Amz-Security-Token=IQoJb3JpZ2luX2VjELr%2F%2F%2F%2F%2F%2F%2F%2F%2F%2FwEaCXVzLWVhc3QtMSJHMEUCIAQzYydT8YUY9FaQDSQhoBuUpgz03PdiGhq8sd0oIoDeAiEAud1qhLQxizbVOIl%2BBJPhxSC9FYIKhoOcjB0oxNJZBogq%2BgMIYxAEGgwwNTkwMDM1NDY4NjUiDG%2FN0T0wxwxgo8fvlCrXAx49MuojjvD5%2F3D4qFfk9CMjm9c5s80hSCJqx53GJKmjlHF243wyxHEwzJjpWgqCyjRFGsDtYEp4DoF2DnrWq4%2B8aVXtevWMoPFW%2FB3OrrIcsmNvSVyE6rDwNOYR1MBlf%2FePBNyEegQv5UIshT1GJzlI6K4Mo%2FsJRBVnJGLmRGIXG4Q%2FvAkGonTB2w6mPx6uT10b9KOklAcYYlMo2VLyQYR%2B2UtOFruEBgz3fPYqowg1iyqChoSeAu8GboWmNgMFVUEb4ug%2FUVIkDcin5iAL1M0%2Fn52LrAM8zn8CH%2Fx%2BhFT3ZV36Q3fjrfhWZoEyzN2SP%2F5VDcyPohB5mwD3L21anRlo0Ylr3POK0Kc65tpir5ztltKmLbA0RjrchqaN2CTsLyR77dy5wQIaf8bSxKtNqdpa5OXVic%2FP%2FPNjgpmajJzsrT5oeXHizp1o1F4EUNcn%2BcoMAKIIhn3JZt89nBjrmZIzffj1MIh3PFUcFJuqBIp60%2BHiSNNbPRjs4XbCQKFxMjhDEk%2FGK0SwTGb6Pk7P2IGViHo9z4ix25iWgH6qJ08bbnDjNOu9Obi0ceMNDEX2s7VeHCyIdzTwwTCiPWI0h5PrV3UpV08zmPnmfRP4VDS7jDtYaXa3szCt4MSFBjqlAUIxD1SX0T5J7ZUYhqqr6SqYvcODFR1ArcuWNv9EqxDOEolU%2FrHktNQ6AeTADoFj4Q3Wl96j%2BydW2e0hshOM4Y5%2BwQTRzddOMPWsnhzNoFKkQzOvDucvVWfMJBxoyuC5fvN3idi4Tl%2BnyOi6DJYXLwOjuetrM8Zp4VSxD91gWPE%2BZf26D9JxHQ%2BbVsvNc3hxB3h3ADoJOhnt%2BBaa385X26MYhWzUBw%3D%3D&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Date=20210528T183333Z&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Expires=300&amp;X-Amz-Credential=ASIAQ3PHCVTY2HHGJ2LK%2F20210528%2Fus-east-1%2Fs3%2Faws4_request&amp;X-Amz-Signature=845bf7080b6306729951759e40caebedcc630a34be3bdbed3cf6f68c58a33065&amp;hash=d4f9019ee1af4c8d9cd99f39429e1243ba03d4afbbb12d2b26a95d54f9d6a626&amp;host=68042c943591013ac2b2430a89b270f6af2c76d8dfd086a07176afe7c76c2c61&amp;pii=S2095756421000222&amp;tid=spdf-5bed2dd4-97d3-4362-abd8-41abea88c91a&amp;sid=8b74e7417f473147011ae096e9b3b2fc3839gxrqa&amp;type=client" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/35/da/35da66ac7c3e1fc6d06723471c92309a2f368be6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.jtte.2021.03.001"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> elsevier.com </button> </a>

A Unified Framework for Structured Graph Learning via Spectral Constraints [article]

Sandeep Kumar, Jiaxi Ying, José Vinícius de M. Cardoso, Daniel Palomar
<span title="2019-04-22">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To impose a particular structure on a graph, we first show how to formulate the combinatorial constraints as an analytical property of the graph matrix.  ...  Then we develop an optimization framework that leverages graph learning with specific structures via spectral constraints on graph matrices.  ...  Now we introduce a general optimization framework for structured graph learning via spectral constraints on the graph matrices, maximize Θ log gdet(Θ) − tr ΘS − αh(Θ), subject to Θ ∈ S Θ , λ T (Θ) ∈ S  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.09792v1">arXiv:1904.09792v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/oyeulr5bcjasbhs2cbeixvk2fu">fatcat:oyeulr5bcjasbhs2cbeixvk2fu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200823021119/https://arxiv.org/pdf/1904.09792v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/63/4c/634c0c19690e136a727fb5bb820912ac6e5e37c0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.09792v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Tracklet Association Tracker: An End-to-End Learning-based Association Approach for Multi-Object Tracking [article]

Han Shen, Lichao Huang, Chang Huang, Wei Xu
<span title="2018-08-05">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The framework aims at gluing feature learning and data association into a unity by a bi-level optimization formulation so that the association results can be directly learned from features.  ...  The separation of the task requires to define a hand-crafted training goal in affinity learning stage and a hand-crafted cost function of data association stage, which prevents the tracking goals from  ...  Bi-level optimization training. We use a three-layer MLP with Leaky ReLU activation for the pairwise network.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1808.01562v1">arXiv:1808.01562v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/krtokutwlrbr7a2t27vc7jzgly">fatcat:krtokutwlrbr7a2t27vc7jzgly</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200827104637/https://arxiv.org/pdf/1808.01562v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/8f/63/8f6364b205d3b53e4e91fc68bd6eae9e6343eabe.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1808.01562v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learning for Graph Matching and Related Combinatorial Optimization Problems

Junchi Yan, Shuang Yang, Edwin Hancock
<span title="">2020</span> <i title="International Joint Conferences on Artificial Intelligence Organization"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vfwwmrihanevtjbbkti2kc3nke" style="color: black;">Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence</a> </i> &nbsp;
This survey gives a selective review of recent development of machine learning (ML) for combinatorial optimization (CO), especially for graph matching.  ...  We further present outlook for the new settings for learning graph matching, and direction towards more integrated combinatorial optimization solvers with prediction models, and also the mutual embrace  ...  They use a bi-directional LSTM [Hochreiter and Schmidhuber, 1997 ] layer with attention for encoding each token to get a sentence representation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2020/683">doi:10.24963/ijcai.2020/683</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ijcai/MathiasKMB20.html">dblp:conf/ijcai/MathiasKMB20</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wzcx476gmvbdtoiqrt3owpzcea">fatcat:wzcx476gmvbdtoiqrt3owpzcea</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201103234817/https://www.ijcai.org/Proceedings/2020/0683.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d0/03/d0039b7268df3487a59eaa6e09216f155ee33d26.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2020/683"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 3,304 results