Papers with linear attention mechanism

3 papers
PermuteFormer: Efficient Relative Position Encoding for Long Sequences (2021.emnlp-main)

Copied to clipboard

Challenge: Existing Transformers that scale to long sequences are not compatible with relative position encoding.
Approach: They propose a Performer-based model with relative position encoding that scales linearly on long sequences.
Outcome: The proposed model outperforms performer on long sequences with no computational overhead and outperformed vanilla Transformer on most of the tasks.
RWKV: Reinventing RNNs for the Transformer Era (2023.findings-emnlp)

Copied to clipboard

Challenge: recurrent neural networks struggle to match the performance of Transformers due to limitations in parallelization and scalability.
Approach: They propose a model architecture that combines the efficient parallelizable training of transformers with the efficient inference of RNNs.
Outcome: The proposed model performs on par with similarly sized RNNs, suggesting future work can leverage this architecture to create more efficient models.
IRIS: Interpretable Retrieval-Augmented Classification for Long Interspersed Document Sequences (2025.acl-long)

Copied to clipboard

Challenge: Existing models for document classification struggle with long-text processing due to quadratic computational complexity in the self-attention module.
Approach: They propose a framework that utilizes retrieval to efficiently classify long documents . they use a quadratic attention matrix to capture dependencies between tokens in an input sequence .
Outcome: The proposed framework excels in clinical note disease risk prediction tasks . it can process arbitrarily long documents without increasing computational cost and trainable on a single GPU.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations