A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1909.08387v3.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Graph Neural Networks for Maximum Constraint Satisfaction
[article]
<span title="2020-02-10">2020</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Other Versions
<span title="2019-09-27">2019</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.08387v2">arXiv:1909.08387v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dv6i2y6oxbhxho4ut7avugdfpy">fatcat:dv6i2y6oxbhxho4ut7avugdfpy</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.08387v2">arXiv:1909.08387v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dv6i2y6oxbhxho4ut7avugdfpy">fatcat:dv6i2y6oxbhxho4ut7avugdfpy</a> </span>
<span title="2019-09-18">2019</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.08387v1">arXiv:1909.08387v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3lt7nbhnfndo3awgzavajdxc7q">fatcat:3lt7nbhnfndo3awgzavajdxc7q</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.08387v1">arXiv:1909.08387v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3lt7nbhnfndo3awgzavajdxc7q">fatcat:3lt7nbhnfndo3awgzavajdxc7q</a> </span>
Many combinatorial optimization problems can be phrased in the language of constraint satisfaction problems. We introduce a graph neural network architecture for solving such optimization problems. The architecture is generic; it works for all binary constraint satisfaction problems. Training is unsupervised, and it is sufficient to train on relatively small instances; the resulting networks perform well on much larger instances (at least 10-times larger). We experimentally evaluate our
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.08387v3">arXiv:1909.08387v3</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gb5kx67bvncfxai2jya5ljudku">fatcat:gb5kx67bvncfxai2jya5ljudku</a>
</span>
more »
... for a variety of problems, including Maximum Cut and Maximum Independent Set. Despite being generic, we show that our approach matches or surpasses most greedy and semi-definite programming based algorithms and sometimes even outperforms state-of-the-art heuristics for the specific problems.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321073020/https://arxiv.org/pdf/1909.08387v3.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]
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.08387v3" 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>