Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
80 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Exploring the Impact of Model Scaling on Parameter-Efficient Tuning (2306.02320v2)

Published 4 Jun 2023 in cs.CL and cs.AI

Abstract: Parameter-efficient tuning (PET) methods can effectively drive extremely large pre-trained LLMs (PLMs) by training only minimal parameters. Different PET methods utilize different manually designed tunable modules. In small PLMs, there are usually noticeable performance differences among PET methods. Nevertheless, as the model scale increases, the performance differences become marginal. Hence, we hypothesize that model scaling mitigates the impact of design differences on PET methods. To investigate this hypothesis, we introduce a more flexible PET method called Arbitrary PET (APET) method. The APET method is compatible with a tunable module, which consists of any number of parameters distributed in arbitrary positions. Then, we utilize it and conduct experiments on 11 NLP tasks across 3 representative PLMs. Our investigations reveal that model scaling (1) mitigates the effects of the positions of tunable parameters on performance, and (2) enables tuning methods to achieve performance comparable to full-parameter fine-tuning by optimizing fewer tunable parameters. Intriguingly, we also observe that tuning methods optimize the similar number of tunable parameters to exceed random guess performance on different tasks. We collectively discuss this phenomenon and the two aforementioned findings from an optimization perspective to understand the underlying mechanisms. These conclusions enhance our understanding of the impact of model scaling on PET and assist in designing more effective and efficient PET methods for PLMs of different scales. The source code can be obtained from this GitHub repository: \url{https://github.com/yushengsu-thu/PET_Scaling}.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. Intrinsic dimensionality explains the effectiveness of language model fine-tuning. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 7319–7328, Online. Association for Computational Linguistics.
  2. BitFit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1–9, Dublin, Ireland. Association for Computational Linguistics.
  3. Johan Bos and Katja Markert. 2005. Recognising textual entailment with logical inference. In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pages 628–635, Vancouver, British Columbia, Canada. Association for Computational Linguistics.
  4. Parameter-efficient fine-tuning design spaces. In The Eleventh International Conference on Learning Representations.
  5. The lottery ticket hypothesis for pre-trained BERT networks. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual.
  6. Palm: Scaling language modeling with pathways.
  7. Evaluating lottery tickets under distributional shifts. In Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019), pages 153–162, Hong Kong, China. Association for Computational Linguistics.
  8. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics.
  9. Parameter-efficient fine-tuning of large-scale pre-trained language models. Nature Machine Intelligence.
  10. William B. Dolan and Chris Brockett. 2005. Automatically constructing a corpus of sentential paraphrases. In Proceedings of the Third International Workshop on Paraphrasing (IWP2005).
  11. Glam: Efficient scaling of language models with mixture-of-experts. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, volume 162 of Proceedings of Machine Learning Research, pages 5547–5569. PMLR.
  12. Rigging the lottery: Making all tickets winners. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event, volume 119 of Proceedings of Machine Learning Research, pages 2943–2952. PMLR.
  13. Multi-news: A large-scale multi-document summarization dataset and abstractive hierarchical model. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1074–1084, Florence, Italy. Association for Computational Linguistics.
  14. SAMSum corpus: A human-annotated dialogue dataset for abstractive summarization. In Proceedings of the 2nd Workshop on New Frontiers in Summarization, pages 70–79, Hong Kong, China. Association for Computational Linguistics.
  15. Parameter-efficient transfer learning with diff pruning. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4884–4896, Online. Association for Computational Linguistics.
  16. Towards a unified view of parameter-efficient transfer learning. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net.
  17. SparseAdapter: An easy approach for improving the parameter-efficiency of adapters. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2184–2190, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  18. Parameter-efficient transfer learning for NLP. In Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, volume 97 of Proceedings of Machine Learning Research, pages 2790–2799. PMLR.
  19. Lora: Low-rank adaptation of large language models. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net.
  20. Sparse structure search for delta tuning. In Advances in Neural Information Processing Systems.
  21. Neural architecture search for parameter-efficient fine-tuning of large pre-trained language models. In Findings of the Association for Computational Linguistics: ACL 2023, pages 8506–8515, Toronto, Canada. Association for Computational Linguistics.
  22. Latent retrieval for weakly supervised open domain question answering. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 6086–6096, Florence, Italy. Association for Computational Linguistics.
  23. The power of scale for parameter-efficient prompt tuning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3045–3059, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
  24. Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4582–4597, Online. Association for Computational Linguistics.
  25. Learning word vectors for sentiment analysis. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 142–150, Portland, Oregon, USA. Association for Computational Linguistics.
  26. Compacter: Efficient low-rank hypercomplex adapter layers. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, pages 1022–1035.
  27. Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05), pages 115–124, Ann Arbor, Michigan. Association for Computational Linguistics.
  28. AdapterFusion: Non-destructive task composition for transfer learning. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 487–503, Online. Association for Computational Linguistics.
  29. When BERT Plays the Lottery, All Tickets Are Winning. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3208–3229, Online. Association for Computational Linguistics.
  30. Exploring low-dimensional intrinsic task subspace via prompt tuning. ArXiv preprint, abs/2110.07867.
  31. Improving language understanding by generative pre-training.
  32. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res., 21:140:1–140:67.
  33. Bloom: A 176b-parameter open-access multilingual language model.
  34. Natural language understanding with the quora question pairs dataset. ArXiv preprint, abs/1907.01041.
  35. Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1631–1642, Seattle, Washington, USA. Association for Computational Linguistics.
  36. On transferability of prompt tuning for natural language processing. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3949–3969, Seattle, United States. Association for Computational Linguistics.
  37. Attention is all you need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pages 5998–6008.
  38. SPoT: Better frozen model adaptation through soft prompt transfer. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5039–5059, Dublin, Ireland. Association for Computational Linguistics.
  39. GLUE: A multi-task benchmark and analysis platform for natural language understanding. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net.
  40. Emergent abilities of large language models. Transactions on Machine Learning Research.
  41. Chain of thought prompting elicits reasoning in large language models.
  42. A broad-coverage challenge corpus for sentence understanding through inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1112–1122, New Orleans, Louisiana. Association for Computational Linguistics.
  43. Zonghan Yang and Yang Liu. 2022. On robust prefix-tuning for text classification. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net.
  44. Different tunes played with equal skill: Exploring a unified optimization subspace for delta tuning.
  45. Autopeft: Automatic configuration search for parameter-efficient fine-tuning. arXiv preprint arXiv:2301.12132.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (12)
  1. Yusheng Su (21 papers)
  2. Chi-Min Chan (18 papers)
  3. Jiali Cheng (16 papers)
  4. Yujia Qin (41 papers)
  5. Yankai Lin (125 papers)
  6. Shengding Hu (34 papers)
  7. Zonghan Yang (23 papers)
  8. Ning Ding (122 papers)
  9. Xingzhi Sun (9 papers)
  10. Guotong Xie (31 papers)
  11. Zhiyuan Liu (433 papers)
  12. Maosong Sun (337 papers)
Citations (4)
View on Semantic Scholar