Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets

[2305.17010] Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets Skip to main content Search Submit Donate Log in Computer Science > Machine Learning arXiv:2305.17010 (cs) [Submitted on 26 May 2023 ( v1 ), last revised 28 Aug 2026 (this version, v4)] Title: Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets Authors: Dinghuai Zhang , Hanjun Dai , Esmeralda S. Whitammer , Aaron Courville , Yoshua Bengio , Ling Pan View PDF HTML (experimental) Abstract: Combinatorial optimization (CO) problems are often NP-hard and thus out of reach for exact algorithms, making them a tempting domain to apply machine learning methods. The highly structured constraints in these problems can hinder either optimization or sampling directly in the solution space. On the other hand, GFlowNets have recently emerged as a powerful machinery to efficiently sample from composite unnormalized densities sequentially and have the potential to amortize such solution-searching processes in CO, as well as generate diverse solution candidates. In this paper, we design Markov decision processes (MDPs) for different combinatorial problems and propose to train conditional GFlowNets to sample from the solution space. Efficient training techniques are also developed to benefit long-range credit assignment. Through extensive experiments on a variety of different CO tasks with synthetic and realistic data, we demonstrate that GFlowNet policies can efficiently find high-quality solutions. Our implementation is open-sourced at this https URL . Comments: NeurIPS 2023 (spotlight); code: this https URL Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Discrete Mathematics (cs.DM); Machine Learning (stat.ML) Cite as: arXiv:2305.17010 [cs.LG] (or arXiv:2305.17010v4 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2305.17010 Focus to learn more arXiv-issued DOI via DataCite Related DOI : https://doi.org/10.52202/075280-0522 Focus to learn more DOI(s) linking to related resources Submission history From: Esmeralda Whitammer [ view email ] [v1] Fri, 26 May 2023 15:13:09 UTC (1,309 KB) [v2] Sat, 7 Oct 2023 02:09:55 UTC (1,326 KB) [v3] Mon, 20 Nov 2023 16:57:12 UTC (1,329 KB) [v4] Fri, 28 Aug 2026 06:31:18 UTC (1,108 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.LG < prev | next > new | recent | 2023-05 Change to browse by: cs cs.AI cs.DM stat stat.ML References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets#684150
• Distributed $(Δ+1)$-Coloring in Graphs of Bounded Neighborhood Independence#924468
• Distributed $(Δ+1)$-Coloring in Graphs of Bounded Neighborhood Independence#920237
• Locating-dominating partitions for some classes of graphs#147107
• Fair Division of Graphs: Beyond Traceability#799152