Papers › PIE: a Parameter and Inference Efficient Solution for Large Scale Knowledge Graph...

PIE: a Parameter and Inference Efficient Solution for Large Scale Knowledge Graph Embedding Reasoning

29 Apr 2022arXiv:2204.13957archive 2025-07-28

Linlin Chao, Xiexiong Lin, Taifeng Wang, Wei Chu

Knowledge graph (KG) embedding methods which map entities and relations to unique embeddings in the KG have shown promising results on many reasoning tasks. However, the same embedding dimension for both dense entities and sparse entities will cause either over parameterization (sparse entities) or under fitting (dense entities). Normally, a large dimension is set to get better performance. Meanwhile, the inference time grows log-linearly with the number of entities for all entities are traversed and compared. Both the parameter and inference become challenges when working with huge amounts of entities. Thus, we propose PIE, a parameter and inference efficient solution. Inspired from tensor decomposition methods, we find that decompose entity embedding matrix into low rank matrices can reduce more than half of the parameters while maintaining comparable performance. To accelerate model inference, we propose a self-supervised auxiliary task, which can be seen as fine-grained entity typing. By randomly masking and recovering entities' connected relations, the task learns the co-occurrence of entity and relations. Utilizing the fine grained typing, we can filter unrelated entities during inference and get targets with possibly sub-linear time requirement. Experiments on link prediction benchmarks demonstrate the proposed key capabilities. Moreover, we prove effectiveness of the proposed solution on the Open Graph Benchmark large scale challenge dataset WikiKG90Mv2 and achieve the state of the art performance.

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

Syntology 15 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 15 samples from 1 repository, 12 ran (12 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 between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

alipay/parameter_inference_efficient_pie officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 15 samples, 12 ran (0 instrument-failed) · 3 unverified report
ant-research/parameter_inference_efficient_pie mentioned on GitHubpytorchApache-2.0Syntology: not harvested 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: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 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.

12ran
3unverified

Licence: 0 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 alipay/parameter_inference_efficient_pie. “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.

alipay/parameter_inference_efficient_pie official repository 15 samples, 12 ran (0 instrument-failed) · 3 unverified
count_all_paths entity_typing/src/utils.py ran Apache-2.0 (permissive) · 43b5e3fa582da3d7 · report fixture: signature inputs:tuple/1/dict · returned dict · level recorded 2026-09-25
get_compatible_batch_size candidate/utils.py ran fingerprinted Apache-2.0 (permissive) · 5d2141cb615d084d · report fixture: signature batch_size:int/0/int, neg_sample_size:int/0/int · returned int · level recorded 2026-09-24
get_params_for_mp entity_typing/src/utils.py ran fingerprinted Apache-2.0 (permissive) · b5db0d52d633b48d · report fixture: signature n_triples:int/0/int · returned tuple · level recorded 2026-09-25
get_partition_dataset candidate/KGDataset.py ran Apache-2.0 (permissive) · f5ccd995ef379580 · report fixture: signature data_path:str/0/str, data_name:str/0/str, part_id:int/0/int · returned tuple · level recorded 2026-09-24
load_model_config in 8 papers candidate/utils.py ran Apache-2.0 (permissive) · fe11f904a96ceb2c · report fixture: signature config_f:str/0/str · returned dict · level recorded 2026-09-24
read_entities entity_typing/src/data_processer.py ran Apache-2.0 (permissive) · fd92338302edcbb5 · report fixture: signature file_name:str/0/str · returned dict · level recorded 2026-09-25
read_relations entity_typing/src/data_processer.py ran Apache-2.0 (permissive) · d2bc5fbe86f233c4 · report fixture: signature file_name:str/0/str, add_reverse:bool/0/bool · returned dict · level recorded 2026-09-24
read_triplets entity_typing/src/data_processer.py ran Apache-2.0 (permissive) · d2294a70e3d013fd · report fixture: signature file_name:str/0/str, entity_dict:dict/0/?, relation_dict:dict/0/?, add_reverse:bool/0/bool · returned ndarray · level recorded 2026-09-24
test_step_loss entity_typing/src/model.py ran Apache-2.0 (permissive) · a29184cfc113cc69 · report fixture: signature model:callable/0/?, batch:dict/0/? · returned float · level recorded 2026-09-24
test_step_score entity_typing/src/model.py ran Apache-2.0 (permissive) · e4b19c01ab75f646 · report fixture: signature model:callable/0/?, batch:Tensor/2/float · returned Tensor · level recorded 2026-09-24
thread_wrapped_func candidate/utils.py ran Apache-2.0 (permissive) · 6949df7260ec105e · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-24
train_step in 47 papers entity_typing/src/model.py ran Apache-2.0 (permissive) · de25933894de2114 · report fixture: signature model:callable/0/?, optimizer:SGD/0/?, batch:dict/0/?, uni_weight:float/0/float · returned float · level recorded 2026-09-24
count_all_paths_with_mp entity_typing/src/utils.py unverified Apache-2.0 (permissive) · 018bf3f65be492cc · report
get_server_partition_dataset candidate/KGDataset.py unverified Apache-2.0 (permissive) · 781f017533eedd24 · report
infer in 29 papers candidate/get_candidate_dgl.py unverified Apache-2.0 (permissive) · ad37003f04543138 · report

Tasks

Entity TypingGraph EmbeddingKnowledge Graph EmbeddingLink PredictionTensor Decomposition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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