mlsanityData to 7 Oct 2026

Distributionally Robust Set Representation Learning Under Inference-Time Element Corruption

arXiv 2605.30089 ↗First posted 28 May 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Standard Set Representation Learning methods typically excel on curated data but often overlook the challenge of inference-time element corruption. This refers to scenarios where deployed models encounter element-level degradations, such as outliers or missing components, that may distort set representation and degrade performance. We propose SW-DRSO, a distributionally robust optimization framework tailored for sets. Rather than minimizing loss solely on observed training data, SW-DRSO optimizes a tractable surrogate of the worst-case expected loss over a family of plausible inference-time variations. We introduce a barycentric adversary that approximates the intractable search over corrupted sets by a differentiable training-time optimization over simplex weights. Extensive experiments across four tasks demonstrate that SW-DRSO effectively enhances robustness against corruption while maintaining high overall performance.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 63 of its 93 references that are in the map. First posted on arXiv 28 May 2026.

Builds on

63 of 93 references.

References · 63

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  4. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  5. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  6. 2021Perceiver: General Perception with Iterative Attentioncited by 1,089
  7. 2017Remote Sensing Image Scene Classification: Benchmark and State of the Artcited by 791
  8. 2017Spectrally-normalized margin bounds for neural networkscited by 681
  9. 2013Network In Networkcited by 600
  10. 2019Generalized Sliced Wasserstein Distancescited by 205
  11. 2022Understanding The Robustness in Vision Transformerscited by 144
  12. 2016Towards a Neural Statisticiancited by 119
38 more
  1. 2026CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verificationcited by 117
  2. 2018Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputscited by 96
  3. 2025AgentAuditor: Human-Level Safety and Security Evaluation for LLM Agentscited by 82
  4. 2019Distributionally Robust Optimization: A Reviewcited by 75
  5. 2019Distributionally Robust Optimization and Generalization in Kernel Methodscited by 73
  6. 2019FSPool: Learning Set Representations with Featurewise Sort Poolingcited by 53
  7. 2024Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimizationcited by 52
  8. 2021Modeling Scale-free Graphs with Hyperbolic Geometry for Knowledge-aware Recommendationcited by 38
  9. 2023RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendationcited by 36
  10. 2023Dynamically Expandable Graph Convolution for Streaming Recommendationcited by 26
  11. 2024Integrating Large Language Models into Recommendation via Mutual Augmentation and Adaptive Aggregationcited by 26
  12. 2019Rep the Set: Neural Networks for Learning Set Representationscited by 22
  13. 2021Learning Prototype-oriented Set Representations for Meta-Learningcited by 19
  14. 2026GAM: Hierarchical Graph-based Agentic Memory for LLM Agentscited by 19
  15. 2022Distributionally Robust Bayesian Optimization with varphi-divergencescited by 16
  16. 2018Learning Representations of Sets through Optimized Permutationscited by 15
  17. 2024DyG-Mamba: Continuous State Space Modeling on Dynamic Graphscited by 15
  18. 2020Principled learning method for Wasserstein distributionally robust optimization with local perturbationscited by 14
  19. 2021Attentive Knowledge-aware Graph Convolutional Networks with Collaborative Guidance for Personalized Recommendationcited by 12
  20. 2024HiHPQ: Hierarchical Hyperbolic Product Quantization for Unsupervised Image Retrievalcited by 11
  21. 2024Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyondcited by 11
  22. 2025CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Codingcited by 11
  23. 2026Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaborationcited by 10
  24. 2024Deep Structural Knowledge Exploitation and Synergy for Estimating Node Importance Value on Heterogeneous Information Networkscited by 9
  25. 2025Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimizationcited by 9
  26. 2024Differentiable Distributionally Robust Optimization Layerscited by 8
  27. 2025Fourier Sliced-Wasserstein Embedding for Multisets and Measurescited by 8
  28. 2023Dynamic Embedding Size Search with Minimum Regret for Streaming Recommender Systemcited by 7
  29. 2026PrefIx: Understand and Adapt to User Preference in Human-Agent Interactioncited by 7
  30. 2026AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompterscited by 7
  31. 2018Deep Perm-Set Net: Learn to predict sets with unknown permutation and cardinality using deep neural networkscited by 6
  32. 2024VersusDebias: Universal Zero-Shot Debiasing for Text-to-Image Models via SLM-Based Prompt Engineering and Generative Adversarycited by 6
  33. 2025Semantic Retrieval Augmented Contrastive Learning for Sequential Recommendationcited by 6
  34. 2025Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safetycited by 6
  35. 2022Bayesian Optimization for Distributionally Robust Chance-constrained Problemcited by 5
  36. 2023Sim2Rec: A Simulator-based Decision-making Approach to Optimize Real-World Long-term User Engagement in Sequential Recommender Systemscited by 5
  37. 2024Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsitycited by 5
  38. 2025Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologiescited by 5

50 most cited of 63 All 63 (JSON)

Built on by

Not cited yet.