Papers › HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification

HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification

24 May 2023arXiv:2305.15182archive 2025-07-28

He Zhu, Chong Zhang, JunJie Huang, Junran Wu, Ke Xu

Hierarchical text classification (HTC) is a challenging subtask of multi-label classification as the labels form a complex hierarchical structure. Existing dual-encoder methods in HTC achieve weak performance gains with huge memory overheads and their structure encoders heavily rely on domain knowledge. Under such observation, we tend to investigate the feasibility of a memory-friendly model with strong generalization capability that could boost the performance of HTC without prior statistics or label semantics. In this paper, we propose Hierarchy-aware Tree Isomorphism Network (HiTIN) to enhance the text representations with only syntactic information of the label hierarchy. Specifically, we convert the label hierarchy into an unweighted tree structure, termed coding tree, with the guidance of structural entropy. Then we design a structure encoder to incorporate hierarchy-aware information in the coding tree into text representations. Besides the text encoder, HiTIN only contains a few multi-layer perceptions and linear transformations, which greatly saves memory. We conduct experiments on three commonly used datasets and the results demonstrate that HiTIN could achieve better test performance and less memory consumption than state-of-the-art (SOTA) methods.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2305.15182")

Code

Syntology Ran 13 of 17 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 3 ran · honoured contract; 5 ran · our draft was wrong; 1 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 12 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

rooooyy/hitin officialmentioned in papermentioned on GitHubpytorch 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

17 samples harvested; 13 ran; 3 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · honoured contract
5ran · our draft was wrong
1ran · fixture could not drive it
4ran
4unverified

Licence: 17 of the 17 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 Rooooyy/HiTIN. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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 “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

CodingTree Rooooyy/HiTIN/models/structure_model/tin.py official repository ran no licence file found · pointer only · 8c8549ef00f962bd · report
CodingTreeNode Rooooyy/HiTIN/models/structure_model/tin.py official repository ran no licence file found · pointer only · 8874b0734542c57c · report
CombineDelta Rooooyy/HiTIN/models/structure_model/tin.py official repository ran · honoured contract no licence file found · pointer only · 27b85c018df3e1ef · report
CompressDelta Rooooyy/HiTIN/models/structure_model/tin.py official repository ran · honoured contract no licence file found · pointer only · 3c6b6d5f29cb86f2 · report
LayerFirst Rooooyy/HiTIN/models/structure_model/tin.py official repository ran · our draft was wrong no licence file found · pointer only · 1b537434cdccd2b8 · report
MLP Rooooyy/HiTIN/models/structure_model/tin.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · 25a0675fc79d400a · report
child_tree_deepth Rooooyy/HiTIN/models/structure_model/tin.py official repository ran · honoured contract no licence file found · pointer only · b16d0d091d08f27f · report
cut_volume Rooooyy/HiTIN/models/structure_model/tin.py official repository ran · fixture could not drive it no licence file found · pointer only · 721b31dc7e862365 · report
get_child_h Rooooyy/HiTIN/models/structure_model/tin.py official repository ran · our draft was wrong no licence file found · pointer only · 76b488bd328d7b46 · report
get_id Rooooyy/HiTIN/models/structure_model/tin.py official repository ran no licence file found · pointer only · ce53a55f5f9e228a · report
graph_parse Rooooyy/HiTIN/models/structure_model/tin.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · fe2b6ce218e73bf2 · report
map_id Rooooyy/HiTIN/models/structure_model/tin.py official repository ran · our draft was wrong no licence file found · pointer only · a2e564a3647ca1cf · report
TINConv Rooooyy/HiTIN/models/structure_model/tin.py official repository unverified no licence file found · pointer only · 845e6369141d563b · report
TreeIsomorphismNetwork Rooooyy/HiTIN/models/structure_model/tin.py official repository unverified no licence file found · pointer only · baa6fae1a00252dc · report
compressNode Rooooyy/HiTIN/models/structure_model/tin.py official repository unverified no licence file found · pointer only · 93521ab59f43b3bb · report
merge Rooooyy/HiTIN/models/structure_model/tin.py official repository unverified no licence file found · pointer only · bc9e8ca43dc38184 · report
update_node identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 33d71761e0a8d2f1 · report

Tasks

Hierarchical Multi-label ClassificationMUlTI-LABEL-ClASSIFICATIONMulti-Label ClassificationMulti-Label Text ClassificationText Classificationtext-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Hierarchical Multi-label Classification New York Times Annotated Corpus HiTIN+BERT Macro F1 69.31 #6 of 7 Archive leaderboard report
Hierarchical Multi-label Classification New York Times Annotated Corpus HiTIN+BERT Micro F1 79.65 #6 of 7 Archive leaderboard report
Hierarchical Multi-label Classification New York Times Annotated Corpus HiTIN Macro F1 61.09 #7 of 7 Archive leaderboard report
Hierarchical Multi-label Classification New York Times Annotated Corpus HiTIN Micro F1 75.13 #7 of 7 Archive leaderboard report
Hierarchical Multi-label Classification RCV1-v2 HiTIN+BERT Macro F1 69.95 #6 of 7 Archive leaderboard report
Hierarchical Multi-label Classification RCV1-v2 HiTIN+BERT Micro F1 86.71 #6 of 7 Archive leaderboard report
Hierarchical Multi-label Classification RCV1-v2 HiTIN Macro F1 64.37 #7 of 7 Archive leaderboard report
Hierarchical Multi-label Classification RCV1-v2 HiTIN Micro F1 84.81 #7 of 7 Archive leaderboard report
Hierarchical Multi-label Classification WOS HiTIN+BERT Macro F1 81.57 #2 of 3 Archive leaderboard report
Hierarchical Multi-label Classification WOS HiTIN+BERT Micro F1 87.19 #2 of 3 Archive leaderboard report
Hierarchical Multi-label Classification WOS HiTIN Macro F1 81.11 #3 of 3 Archive leaderboard report
Hierarchical Multi-label Classification WOS HiTIN Micro F1 86.66 #3 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionConvolutionFPNHTCRPNRoIAlignTest

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