mlsanityData to 7 Oct 2026

Pointer Networks

arXiv 1506.03134 ↗First posted 9 Jun 2015stat.ML cs.CG cs.LGcited by 882

Not on the map. Why?

Abstract (arXiv)

We introduce a new neural architecture to learn the conditional probability of an output sequence with elements that are discrete tokens corresponding to positions in an input sequence. Such problems cannot be trivially addressed by existent approaches such as sequence-to-sequence and Neural Turing Machines, because the number of target classes in each step of the output depends on the length of the input, which is variable. Problems such as sorting variable sized sequences, and various combinatorial optimization problems belong to this class. Our model solves the problem of variable size output dictionaries using a recently proposed mechanism of neural attention. It differs from the previous attention attempts in that, instead of using attention to blend hidden units of an encoder to a context vector at each decoder step, it uses attention as a pointer to select a member of the input sequence as the output. We call this architecture a Pointer Net (Ptr-Net). We show Ptr-Nets can be used to learn approximate solutions to three challenging geometric problems -- finding planar convex hulls, computing Delaunay triangulations, and the planar Travelling Salesman Problem -- using training examples alone. Ptr-Nets not only improve over sequence-to-sequence with input attention, but also allow us to generalize to variable size output dictionaries. We show that the learnt models generalize beyond the maximum lengths they were trained on. We hope our results on these tasks will encourage a broader exploration of neural learning for discrete problems.

Key facts. Cited by 882 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Jun 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 220; 2022: 143; 2023: 136; 2024: 129; 2025: 128; 2026: 126.

882 papers.

Sort:

By area:

  1. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
  2. 2022What Can Transformers Learn In-Context? A Case Study of Simple Function Classescited by 700
  3. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 616
  4. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 457
  5. 2021Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depthcited by 411
  6. 2021QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarizationcited by 363
  7. 2021Combinatorial optimization and reasoning with graph neural networkscited by 267
  8. 2024Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Modelcited by 258
  9. 2021Mind the Gap: Assessing Temporal Generalization in Neural Language Modelscited by 226
  10. 2021End-to-End Constrained Optimization Learning: A Surveycited by 154
  11. 2021A Unified Generative Framework for Various NER Subtaskscited by 141
  12. 2023Neural Combinatorial Optimization with Heavy Decoder: Toward Large Scale Generalizationcited by 140
38 more
  1. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  2. 2021Airbert: In-domain Pretraining for Vision-and-Language Navigationcited by 129
  3. 2022DIMES: A Differentiable Meta Solver for Combinatorial Optimization Problemscited by 127
  4. 2022SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebookscited by 121
  5. 2022Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimizationcited by 118
  6. 2021Learning to Delegate for Large-scale Vehicle Routingcited by 108
  7. 2021Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformercited by 108
  8. 2021LambdaNetworks: Modeling Long-Range Interactions Without Attentioncited by 107
  9. 2021Combinatorial Optimization with Physics-Inspired Graph Neural Networkscited by 107
  10. 2022The CLRS Algorithmic Reasoning Benchmarkcited by 103
  11. 2021NeuroLKH: Combining Deep Learning Model with Lin-Kernighan-Helsgaun Heuristic for Solving the Traveling Salesman Problemcited by 102
  12. 2024BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometrycited by 101
  13. 2021Efficient Active Search for Combinatorial Optimization Problemscited by 99
  14. 2021A Unified Generative Framework for Aspect-Based Sentiment Analysiscited by 97
  15. 2021Deep Policy Dynamic Programming for Vehicle Routing Problemscited by 94
  16. 2021Matrix Encoding Networks for Neural Combinatorial Optimizationcited by 89
  17. 2021Learning Collaborative Policies to Solve NP-hard Routing Problemscited by 86
  18. 2021Video Summarization Using Deep Neural Networks: A Surveycited by 85
  19. 2022Simulation-guided Beam Search for Neural Combinatorial Optimizationcited by 84
  20. 2021Computer-Aided Design as Languagecited by 82
  21. 2023GLOP: Learning Global Partition and Local Construction for Solving Large-scale Routing Problems in Real-timecited by 82
  22. 2023Learning to Search Feasible and Infeasible Regions of Routing Problems with Flexible Neural k-Optcited by 81
  23. 2023BQ-NCO: Bisimulation Quotienting for Efficient Neural Combinatorial Optimizationcited by 80
  24. 2022SolidGen: An Autoregressive Model for Direct B-rep Synthesiscited by 78
  25. 2023DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimizationcited by 77
  26. 2023Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought Methodcited by 76
  27. 2024CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLMcited by 74
  28. 2024Safeguarding Large Language Models: A Surveycited by 73
  29. 2021LaTr: Layout-Aware Transformer for Scene-Text VQAcited by 72
  30. 2021Machine Learning for Electronic Design Automation: A Surveycited by 71
  31. 2022Limitations of Language Models in Arithmetic and Symbolic Inductioncited by 71
  32. 2021Graph Neural Network Guided Local Search for the Traveling Salesperson Problemcited by 70
  33. 2023RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmarkcited by 70
  34. 2024MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Expertscited by 69
  35. 2021SketchGen: Generating Constrained CAD Sketchescited by 68
  36. 2023Towards Omni-generalizable Neural Methods for Vehicle Routing Problemscited by 68
  37. 2021Vitruvion: A Generative Model of Parametric CAD Sketchescited by 66
  38. 2021Language-Agnostic Representation Learning of Source Code from Structure and Contextcited by 63

50 most cited of 882 All 882 (JSON)