Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.17140 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916705334198272 |
|---|---|
| author | Ranjan, Ashish Agarwal, Ayush Barot, Shalin Kumar, Sushant |
| author_facet | Ranjan, Ashish Agarwal, Ayush Barot, Shalin Kumar, Sushant |
| contents | Temporal set prediction involves forecasting the elements that will appear in the next set, given a sequence of prior sets, each containing a variable number of elements. Existing methods often rely on intricate architectures with substantial computational overhead, which hampers their scalability. In this work, we introduce a novel and scalable framework that leverages permutation-equivariant and permutation-invariant transformations to efficiently model set dynamics. Our approach significantly reduces both training and inference time while maintaining competitive performance. Extensive experiments on multiple public benchmarks show that our method achieves results on par with or superior to state-of-the-art models across several evaluation metrics. These results underscore the effectiveness of our model in enabling efficient and scalable temporal set prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_17140 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Scalable Permutation-Aware Modeling for Temporal Set Prediction Ranjan, Ashish Agarwal, Ayush Barot, Shalin Kumar, Sushant Machine Learning Artificial Intelligence Temporal set prediction involves forecasting the elements that will appear in the next set, given a sequence of prior sets, each containing a variable number of elements. Existing methods often rely on intricate architectures with substantial computational overhead, which hampers their scalability. In this work, we introduce a novel and scalable framework that leverages permutation-equivariant and permutation-invariant transformations to efficiently model set dynamics. Our approach significantly reduces both training and inference time while maintaining competitive performance. Extensive experiments on multiple public benchmarks show that our method achieves results on par with or superior to state-of-the-art models across several evaluation metrics. These results underscore the effectiveness of our model in enabling efficient and scalable temporal set prediction. |
| title | Scalable Permutation-Aware Modeling for Temporal Set Prediction |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2504.17140 |