P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks

Liu, Xiao; Ji, Kaixuan; Fu, Yicheng; Tam, Weng Lam; Du, Zhengxiao; Yang, Zhilin; Tang, Jie

doi:10.48550/arxiv.2110.07602

Cited by 64 publications

(93 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have showcased how to attach them to a single MSA layer in Section 4.1. Most existing prompt-related work simply place prompts only at the first MSA [60,24], or at every MSA layer [25,29]. However, we argue that it is crucial to explore where and how to attach both types of prompts, under the continual visual learning setting.…”

Section: Prompt Attaching: Where and How?mentioning

confidence: 99%

DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning

Wang¹,

Zhang²,

Ebrahimi³

et al. 2022

Preprint

View full text Add to dashboard Cite

Continual learning aims to enable a single model to learn a sequence of tasks without catastrophic forgetting. Top-performing methods usually require a rehearsal buffer to store past pristine examples for experience replay, which, however, limits their practical value due to privacy and memory constraints. In this work, we present a simple yet effective framework, DualPrompt, which learns a tiny set of parameters, called prompts, to properly instruct a pre-trained model to learn tasks arriving sequentially without buffering past examples. DualPrompt presents a novel approach to attach complementary prompts to the pre-trained backbone, and then formulates the objective as learning task-invariant and task-specific "instructions". With extensive experimental validation, DualPrompt consistently sets state-of-the-art performance under the challenging class-incremental setting. In particular, DualPrompt outperforms recent advanced continual learning methods with relatively large buffer sizes. We also introduce a more challenging benchmark, Split ImageNet-R, to help generalize rehearsal-free continual learning research. Source code is available at https://github.com/google-research/l2p.

show abstract

Section: Prompt Attaching: Where and How?mentioning

confidence: 99%

DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning

Wang¹,

Zhang²,

Ebrahimi³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…For a given task, a fixed number of continuous token embeddings is optimized when concatenated to the input embeddings of each training example (illustrated in Figure 1a). When trained on a single dataset (and when given access to a largeenough model), prompt tuning has been shown to yield performance competitive with fine tuning Liu et al, 2021). This is an inspiring finding, since the fraction of parameters trained during prompt tuning is tiny relative to full model size (∼ 0.001%).…”

Section: The Id-pt Architecturementioning

confidence: 94%

Standing on the Shoulders of Giant Frozen Language Models

Levine¹,

Dalmedigos²,

Ram³

et al. 2022

Preprint

View full text Add to dashboard Cite

Huge pretrained language models (LMs) have demonstrated surprisingly good zero-shot capabilities on a wide variety of tasks. This gives rise to the appealing vision of a single, versatile model with a wide range of functionalities across disparate applications. However, current leading techniques for leveraging a "frozen" LM-i.e., leaving its weights untouched-still often underperform fine-tuning approaches which modify these weights in a task-dependent way. Those, in turn, suffer forgetfulness and compromise versatility, suggesting a tradeoff between performance and versatility. The main message of this paper is that current frozenmodel techniques such as prompt tuning are only the tip of the iceberg, and more powerful methods for leveraging frozen LMs can do just as well as fine tuning in challenging domains without sacrificing the underlying model's versatility. To demonstrate this, we introduce three novel methods for leveraging frozen models: input-dependent prompt tuning, frozen readers, and recursive LMs, each of which vastly improves on current frozen-model approaches. Indeed, some of our methods even outperform fine-tuning approaches in domains currently dominated by the latter. The computational cost of each method is higher than that of existing frozen model methods, but still negligible relative to a single pass through a huge frozen LM. Each of these methods constitutes a meaningful contribution in its own right, but by presenting these contributions together we aim to convince the reader of a broader message that goes beyond the details of any given method: that frozen models have untapped potential and that fine-tuning is often unnecessary.

show abstract

“…Currently, prompt tuning is one of the most parameter-efficient methods for large language models [45,14,53]. Liu et al [54] introduce several tricks to improve prompt tuning, An et al [55] tune prompts along with input embeddings for boost in performance, and Chen et al [56] improve prompt embeddings through continued pre-training. Given optimization difficulties when training prompt embeddings, Diao et al [57] recently used black-box optimization to train prompt embeddings without requiring gradients.…”

Section: Related Workmentioning

confidence: 99%

Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning

Liu¹,

Tam²,

Muqeeth³

et al. 2022

Preprint

View full text Add to dashboard Cite

Few-shot in-context learning (ICL) enables pre-trained language models to perform a previously-unseen task without any gradient-based training by feeding a small number of training examples as part of the input. ICL incurs substantial computational, memory, and storage costs because it involves processing all of the training examples every time a prediction is made. Parameter-efficient fine-tuning (e.g. adapter modules, prompt tuning, sparse update methods, etc.) offers an alternative paradigm where a small set of parameters are trained to enable a model to perform the new task. In this paper, we rigorously compare few-shot ICL and parameter-efficient fine-tuning and demonstrate that the latter offers better accuracy as well as dramatically lower computational costs. Along the way, we introduce a new parameter-efficient fine-tuning method called (IA) 3 that scales activations by learned vectors, attaining stronger performance while only introducing a relatively tiny amount of new parameters. We also propose a simple recipe based on the T0 model [1] called T-Few that can be applied to new tasks without task-specific tuning or modifications. We validate the effectiveness of T-Few on completely unseen tasks by applying it to the RAFT benchmark [2], attaining super-human performance for the first time and outperforming the state-of-the-art by 6% absolute. All of the code used in our experiments is publicly available. 1 * Equal contribution. 1 https://github.com/r-three/t-few Preprint. Under review.

show abstract

P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks

Cited by 64 publications

References 42 publications

DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning

DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning

Standing on the Shoulders of Giant Frozen Language Models

Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning

Contact Info

Product

Resources

About