paper-with-me

Papers

Increasing Learning Efficiency of Self-Attention Networks through Direct Position Interactions, Learnable Temperature, and Convoluted Attention

2020-12-01 · COLING 2020 8 · Philipp Dufter, Martin Schmitt, Hinrich Sch{\"u}tze

Self-Attention Networks (SANs) are an integral part of successful neural architectures such as Transformer (Vaswani et al., 2017), and thus of pretrained language models such as BERT (Devlin et al., 2019) or GPT-3 (Brown et al., 2020). Training SANs on a task or pretraining them on language modeling requires large amounts of data and compute resources. We are searching for modifications to SANs that enable faster learning, i.e., higher accuracies after fewer update steps. We investigate three modifications to SANs: direct position interactions, learnable temperature, and convoluted attention. When evaluating them on part-of-speech tagging, we find that direct position interactions are an alternative to position embeddings, and convoluted attention has the potential to speed up the learning process.

📄 PDF Abstract BibTeX

Code (1)

pdufter/convatt 공식 구현 tf

Tasks

Language ModelingLanguage ModellingPart-Of-Speech TaggingPosition

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…

Similar Papers 제목 키워드 기반

The Depth-to-Width Interplay in Self-Attention

2020-06-22 · NeurIPS 2020 12 · Yoav Levine, Noam Wies, Or Sharir, Hofit Bata 외

Self-attention architectures, which are rapidly pushing the frontier in natural language processing, demonstrate a surprising depth-inefficient behavior: previous works indicate that increasing the internal representatio…

A Unified Sparse Attention via Multi-Granularity Compression

2025-12-16 · Siran Liu, Zane Cao, Yongchao He arxiv

Efficient long-context understanding and reasoning are increasingly vital for large language model (LLM) applications such as multi-turn dialogue and program analysis. However, the core self-attention mechanism scales qu…

Long-Context Understanding

Self-Selected Attention Span for Accelerating Large Language Model Inference

2024-04-14 · Tian Jin, Wanzin Yazar, Zifei Xu, Sayeh Sharify 외

Large language models (LLMs) can solve challenging tasks. However, their inference computation on modern GPUs is highly inefficient due to the increasing number of tokens they must attend to as they generate new ones. To…

ArticlesLanguage ModelingLanguage ModellingLarge Language Model

Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few

2025-09-21 · Qishuai Wen, Zhiyuan Huang, Chun-Guang Li arxiv

Attention mechanisms have achieved significant empirical success in multiple fields, but their underlying optimization objectives remain unclear yet. Moreover, the quadratic complexity of self-attention has become increa…

APCE: Adaptive Progressive Context Expansion for Long Context Processing

2025-10-14 · Baisub Lee, Sanghyun Byun, Mohanad Odema, Jung Guack 외 arxiv

Deploying useful Long-Context Transformer Models (LCTMs) requires addressing two key challenges: (1) A growing memory footprint due to quadratic self-attention and linear KV-cache scaling in memory as sequence length inc…

Semantic Similarity