Challenge: Several methods have been proposed to improve the inference efficiency of transformer-based models.
Approach: They propose a new adaptive inference method that takes into account the hardness of input samples.
Outcome: The proposed model outperforms or complements existing per-sample adaptive inference methods in terms of accuracy vs. FLOPs and can be applied to compressed and efficient transformer encoders to further improve their efficiency.

Similar Papers

AdapterDrop: On the Efficiency of Adapters in Transformers (2021.emnlp-main)

Copied to clipboard

Challenge: Recent approaches to transformer models are expensive to fine-tune, slow for inference, and have large storage requirements.
Approach: They propose a method to remove adapters from transformer layers during training and inference . they show that AdapterDrop can dynamically reduce computational overhead .
Outcome: The proposed approach reduces computational overhead while maintaining performance over multiple tasks with minimal loss of performance.
Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference (2023.findings-acl)

Copied to clipboard

Challenge: Pre-trained sequence-to-sequence models have advanced the state of the art on text generation tasks.
Approach: They introduce a modular encoder-decoder framework for flexible sequence-to-sequence model compression.
Outcome: The proposed framework can achieve flexible compression ratios from 1.1x to 6x with little to moderate relative performance drop.
Understanding and Overcoming the Challenges of Efficient Transformer Quantization (2021.emnlp-main)

Copied to clipboard

Challenge: Recent advances in transformer quantization have shown remarkable improvement in many Natural Language Processing tasks and beyond.
Approach: They propose a novel quantization scheme for transformers that can be quantized to ultra-low bit-widths, leading to significant memory savings with a minimum accuracy loss.
Outcome: The proposed methods achieve state-of-the-art results on the GLUE benchmark using BERT, while preserving memory and accuracy.
Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers (2021.findings-emnlp)

Copied to clipboard

Challenge: Recent improvements in NLP tasks can be attributed to the Transformer model.
Approach: They propose to use parameter-sharing methods to reduce parameter budgets in generative models by using sandwich-style parameter sharing and self-attentive embedding factorization.
Outcome: The proposed model outperforms the current RNN model even with significantly fewer parameters.
Transformers as Transducers (2025.tacl-1)

Copied to clipboard

Challenge: Using finite transducers, we find that transformers can express large classes of (total functional) transductions.
Approach: They extend existing RASP programming language to sequence-to-sequence transductions and introduce two new extensions.
Outcome: The proposed model can express surprisingly large classes of (total functional) transductions.
DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers (2024.findings-naacl)

Copied to clipboard

Challenge: Existing interpretability methods have been proposed to interpret the inner workings of Transformer models at different levels of precision and complexity.
Approach: They propose a method to analyze encoder-decoder Transformers by using the decoder module Model Output encoder to cross-attend representations of intermediate encoder activations instead of using the default output.
Outcome: The proposed method maps uninterpretable representations to human-interpreted sequences of words or symbols, shedding new light on the information flow in this popular but understudied class of models.
On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers (2021.findings-acl)

Copied to clipboard

Challenge: Recent work shows that attention can be pruned to zeros with minimal loss in accuracy.
Approach: They propose a pruning technique which quantizes attention to a 3-bit format without retraining . they find that 80% of attention values can be pruned to zeros with minimal loss in accuracy .
Outcome: The proposed approach produces only a few unique attention values with minimal loss in accuracy.
On Sparsifying Encoder Outputs in Sequence-to-Sequence Models (2021.findings-acl)

Copied to clipboard

Challenge: Using sequence-to-sequence models, encoder outputs are usually transferred to the decoder for generation, but in this study, encoded outputs can be compressed to shorten the sequence for decoding.
Approach: They propose to use a stochastic gate-based algorithm to mask encoder outputs to shorten the sequence delivered for decoding.
Outcome: The proposed model can be used to shorten encoder outputs to short a sequence . the proposed model yields a speedup of up to 1.65 on document summarization and 1.20 on character-based machine translation tasks.
On the Benefits of Learning to Route in Mixture-of-Experts Models (2023.emnlp-main)

Copied to clipboard

Challenge: Existing Mixture-of-Expert (MoE) models allow us to scale up model sizes while keeping the amount of compute time fixed.
Approach: They propose to use a router to route inputs to experts in a layer to scale up model sizes while keeping the amount of compute time fixed.
Outcome: The proposed model scales up with the help of a router that routes input tokens to experts in a layer and shows that it is more efficient than a non-trainable router.
Optimizing Deeper Transformers on Small Datasets (2021.acl-long)

Copied to clipboard

Challenge: a common belief that training deep transformers from scratch requires large datasets is wrong . however, with proper initialization and optimization, the benefits of very deep transformer can carry over to challenging tasks with small datasets.
Approach: They train 48 layers of transformers from pre-trained RoBERTa and 24 relation-aware layers from scratch.
Outcome: The proposed scheme achieves state-of-the-art performance on a text-to-sql parsing benchmark . it uses 24 fine-tuned layers from pre-trained RoBERTa and 24 relation-aware layers from scratch .

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