Papers › Learning to Augment for Data-Scarce Domain BERT Knowledge Distillation

Learning to Augment for Data-Scarce Domain BERT Knowledge Distillation

20 Jan 2021arXiv:2101.08106archive 2025-07-28

Lingyun Feng, Minghui Qiu, Yaliang Li, Hai-Tao Zheng, Ying Shen

Despite pre-trained language models such as BERT have achieved appealing performance in a wide range of natural language processing tasks, they are computationally expensive to be deployed in real-time applications. A typical method is to adopt knowledge distillation to compress these large pre-trained models (teacher models) to small student models. However, for a target domain with scarce training data, the teacher can hardly pass useful knowledge to the student, which yields performance degradation for the student models. To tackle this problem, we propose a method to learn to augment for data-scarce domain BERT knowledge distillation, by learning a cross-domain manipulation scheme that automatically augments the target with the help of resource-rich source domains. Specifically, the proposed method generates samples acquired from a stationary distribution near the target data and adopts a reinforced selector to automatically refine the augmentation strategy according to the performance of the student. Extensive experiments demonstrate that the proposed method significantly outperforms state-of-the-art baselines on four different tasks, and for the data-scarce domains, the compressed student models even perform better than the original large teacher model, with much fewer parameters (only ∼13.3%) when only a few labeled examples available.

PaperPDFCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 13 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: found in paper text by Syntology: 15 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

huawei-noah/Pretrained-Language-Model found in paper text by SyntologySyntology: 15 samples, 2 ran (0 instrument-failed) · 13 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 13 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran
13unverified

Licence: 15 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from huawei-noah/Pretrained-Language-Model. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

huawei-noah/Pretrained-Language-Model found in paper text by Syntology 15 samples, 2 ran (0 instrument-failed) · 13 unverified
SuperBertIntermediate AutoTinyBERT/transformer/modeling_super_kd.py ran fingerprinted no licence file found · pointer only · c1293a0be49a8674 · report fixture: signature hidden_states:Tensor/2/float, sample_embed_dim:int/0/int, intermediate_size:int/0/int · returned Tensor · level recorded 2026-09-24
SuperBertPooler AutoTinyBERT/transformer/modeling_super_kd.py ran fingerprinted no licence file found · pointer only · e6311f65af5f9840 · report fixture: signature hidden_states:Tensor/3/float, sample_hidden_dim:int/0/int · returned Tensor · level recorded 2026-09-24
BertConfig in 14 papers AutoTinyBERT/transformer/modeling_super_kd.py unverified no licence file found · pointer only · 92bb80eba426ec5f · report
BertPreTrainedModel in 7 papers AutoTinyBERT/transformer/modeling_super_kd.py unverified no licence file found · pointer only · aa473329a2bdbd95 · report
SuperBertAttention AutoTinyBERT/transformer/modeling_super_kd.py unverified no licence file found · pointer only · 334a8d97f2ffa8a3 · report
SuperBertEmbeddings AutoTinyBERT/transformer/modeling_super_kd.py unverified no licence file found · pointer only · 1c3e57fe19c49c14 · report
SuperBertEncoder AutoTinyBERT/transformer/modeling_super_kd.py unverified no licence file found · pointer only · 4cb493cd45952cc0 · report
SuperBertLayer AutoTinyBERT/transformer/modeling_super_kd.py unverified no licence file found · pointer only · 977b5ff098ce7872 · report
SuperBertLayerNorm AutoTinyBERT/transformer/modeling_super_kd.py unverified no licence file found · pointer only · e86b5457a91cc855 · report
SuperBertModel AutoTinyBERT/transformer/modeling_super_kd.py unverified no licence file found · pointer only · cd3c1431cd8eacc2 · report
SuperBertOutput AutoTinyBERT/transformer/modeling_super_kd.py unverified no licence file found · pointer only · f4e5fbf0df9c65ad · report
SuperBertSelfAttention AutoTinyBERT/transformer/modeling_super_kd.py unverified no licence file found · pointer only · a98f9a3c4ea098b0 · report
SuperBertSelfOutput AutoTinyBERT/transformer/modeling_super_kd.py unverified no licence file found · pointer only · 10cb79ce31e3d2ce · report
SuperEmbedding AutoTinyBERT/transformer/modeling_super_kd.py unverified no licence file found · pointer only · 981046902300b03e · report
SuperLinear AutoTinyBERT/transformer/modeling_super_kd.py unverified no licence file found · pointer only · 9c9f54b844986280 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Learning to Augment for Data-Scarce Domain BERT Knowledge Distillation (graph method: Learning to Augment for Data-Scarce Domain BERT Knowledge Distillation). 27 bricks; individually on a fixture: 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 19 unverified. The assembly has not been run end-to-end.

  1. SuperBertModel entry · level 0 · unverified · cd3c1431cd8eacc2
  2. BertPreTrainedModel helper · level 0 · unverified · aa473329a2bdbd95
  3. SuperBertEmbeddings model · level 0 · unverified · 1c3e57fe19c49c14
  4. SuperBertEncoder model · level 0 · unverified · 4cb493cd45952cc0
  5. SuperBertPooler helper · level 1 · ran · e6311f65af5f9840
  6. SuperLinear model · level 0 · unverified · 9c9f54b844986280
  7. BertConfig helper · level 0 · unverified · 92bb80eba426ec5f
  8. SuperBertLayerNorm helper · level 0 · unverified · e86b5457a91cc855
  9. cached_path helper · level 0 · unverified · ea4ad38c9db984c5
  10. SuperEmbedding model · level 0 · unverified · 981046902300b03e
  11. SuperBertLayer model · level 0 · unverified · 977b5ff098ce7872
  12. sample_bias helper · level 1 · ran · our draft was wrong · 8f3031bdf0cdcbce
  13. sample_weight helper · level 1 · ran · our draft was wrong · 7ae41cd971c17070
  14. get_from_cache helper · level 0 · unverified · 317c17bb5ff9da3f
  15. SuperBertAttention helper · level 0 · unverified · 334a8d97f2ffa8a3
  16. SuperBertIntermediate model · level 1 · ran · c1293a0be49a8674
  17. SuperBertOutput model · level 0 · unverified · f4e5fbf0df9c65ad
  18. http_get helper · level 0 · unverified · 18f49ada16168f38
  19. s3_etag helper · level 0 · unverified · 51dd06ec77c8a8d1
  20. s3_get helper · level 0 · unverified · 1079045e75efbf23
  21. url_to_filename helper · level 1 · ran · our draft was wrong · 5eff22fa0a651276
  22. SuperBertSelfAttention model · level 0 · unverified · a98f9a3c4ea098b0
  23. SuperBertSelfOutput model · level 0 · unverified · 10cb79ce31e3d2ce
  24. s3_request helper · level 1 · ran · our draft was wrong · 7661139be003d514
  25. split_s3_path helper · level 0 · unverified · d3852f416bfe86c3
  26. gelu helper · level 1 · ran · honoured contract · fdc64f4c72036ae4
  27. swish helper · level 2 · ran · our draft was wrong · 0f786c407fb1ee4c

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2101.08106") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Knowledge Distillation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutKnowledge DistillationLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections