mlsanityData to 7 Oct 2026

ML4CO-KIDA: Knowledge Inheritance in Dataset Aggregation

arXiv 2201.10328 ↗First posted 25 Jan 2022cs.AI cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

The Machine Learning for Combinatorial Optimization (ML4CO) NeurIPS 2021 competition aims to improve state-of-the-art combinatorial optimization solvers by replacing key heuristic components with machine learning models. On the dual task, we design models to make branching decisions to promote the dual bound increase faster. We propose a knowledge inheritance method to generalize knowledge of different models from the dataset aggregation process, named KIDA. Our improvement overcomes some defects of the baseline graph-neural-networks-based methods. Further, we won the 1textsuperscriptst Place on the dual task. We hope this report can provide useful experience for developers and researchers. The code is available at https://github.com/megvii-research/NeurIPS2021-ML4CO-KIDA.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 7 of its 21 references that are in the map. First posted on arXiv 25 Jan 2022.

Builds on

7 of 21 references.

References · 7

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  3. 2018Born Again Neural Networkscited by 539
  4. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  5. 2017Snapshot Ensembles: Train 1, get M for freecited by 349
  6. 2019Exact Combinatorial Optimization with Graph Convolutional Neural Networkscited by 313
  7. 2018Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environmentscited by 19

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2; 2024: 3; 2025: 2.

9 papers.

  1. 2023Learning Cut Selection for Mixed-Integer Linear Programming via Hierarchical Sequence Modelcited by 44
  2. 2022Deep Reinforcement Learning for Exact Combinatorial Optimization: Learning to Branchcited by 12
  3. 2024Learning to Cut via Hierarchical Sequence/Set Model for Efficient Mixed-Integer Programmingcited by 12
  4. 2022Perceptual Conversational Head Generation with Regularized Driver and Enhanced Renderercited by 11
  5. 2025Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Modelcited by 7
  6. 2024Offline Reinforcement Learning for Learning to Dispatch for Job Shop Schedulingcited by 6
  7. 2024Recent Advances in Attack and Defense Approaches of Large Language Modelscited by 5
  8. 2023Exact Combinatorial Optimization with Temporo-Attentional Graph Neural Networkscited by 3
  9. 2025Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniquescited by 0