Papers › Graph-based Knowledge Distillation by Multi-head Attention Network

Graph-based Knowledge Distillation by Multi-head Attention Network

4 Jul 2019arXiv:1907.02226archive 2025-07-28

Seunghyun Lee, Byung Cheol Song

Knowledge distillation (KD) is a technique to derive optimal performance from a small student network (SN) by distilling knowledge of a large teacher network (TN) and transferring the distilled knowledge to the small SN. Since a role of convolutional neural network (CNN) in KD is to embed a dataset so as to perform a given task well, it is very important to acquire knowledge that considers intra-data relations. Conventional KD methods have concentrated on distilling knowledge in data units. To our knowledge, any KD methods for distilling information in dataset units have not yet been proposed. Therefore, this paper proposes a novel method that enables distillation of dataset-based knowledge from the TN using an attention network. The knowledge of the embedding procedure of the TN is distilled to graph by multi-head attention (MHA), and multi-task learning is performed to give relational inductive bias to the SN. The MHA can provide clear information about the source dataset, which can greatly improves the performance of the SN. Experimental results show that the proposed method is 7.05% higher than the SN alone for CIFAR100, which is 2.46% higher than the state-of-the-art.

PaperPDFCodeCode Syntology ran

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

The archive's official repository (sseung0703/Knowledge_distillation_via_TF2.0) was not harvested; the 18 samples below come from 1 community repository.

Syntology 18 code samples harvested from 1 repository linked to this paper: 0 ran · 18 unverified.

By repository: community (archive-listed): 18 samples from 1 repository, 0 ran (0 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.

sseung0703/Knowledge_distillation_via_TF2.0 officialmentioned on GitHubtfSyntology: not harvested report
sseung0703/KD_methods_with_TF mentioned on GitHubtfMITSyntology: 18 samples, 0 ran · 18 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

18 samples harvested: 0 ran · 18 unverified. 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.

18unverified

Licence: 0 of the 18 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 sseung0703/KD_methods_with_TF. “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. “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.

sseung0703/KD_methods_with_TF community (archive-listed) 18 samples, 0 ran · 18 unverified
AB_distillation nets/Multiple.py unverified MIT (permissive) · fa85bb41a865fdca · report
Attention_head nets/Relation.py unverified MIT (permissive) · aa0940bdc0c62f7c · report
Attention_transfer nets/Multiple.py unverified MIT (permissive) · ca4bc2eab0f28657 · report
Cifar100 dataloader.py unverified MIT (permissive) · 5c6688b3a8175162 · report
DML nets/Response.py unverified MIT (permissive) · 991dc3b2233b9039 · report
Dataloader dataloader.py unverified MIT (permissive) · 333c5cd9cd3d43b5 · report
FSP nets/Shared.py unverified MIT (permissive) · 985f1187d24bf1ba · report
Factor_Transfer nets/Response.py unverified MIT (permissive) · af573b60ae262326 · report
FitNet nets/Multiple.py unverified MIT (permissive) · 15962ff839fd0f61 · report
Optimizer_w_DML op_util.py unverified MIT (permissive) · 8c917630c7f3610d · report
Optimizer_w_Distillation op_util.py unverified MIT (permissive) · 708382ba3e636f17 · report
Optimizer_w_Initializer op_util.py unverified MIT (permissive) · d5bd3262a6641027 · report
RKD nets/Relation.py unverified MIT (permissive) · 2a07b6ca793208a0 · report
SVD nets/SVP.py unverified MIT (permissive) · 898e7c28a1d56867 · report
SVD_eid nets/SVP.py unverified MIT (permissive) · f49f271ffa39ed4e · report
Soft_logits nets/Response.py unverified MIT (permissive) · 7c683b4652eec88b · report
learning_rate_scheduler train_w_distill.py unverified MIT (permissive) · 3fef491ca58b676b · report
removenan nets/SVP.py unverified MIT (permissive) · 801ed5a418c05524 · report

Tasks

Inductive BiasKnowledge DistillationMulti-Task LearningTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionLinear LayerMulti-Head AttentionSoftmax

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