AI Paper Atlas

Research map / Federated learning and privacy / Privacy attacks and secure learning

PCFormer: Accelerating Privacy-preserving Transformer Inference by Partition and Combination

Bo Zeng, Zhi Pang, Yuyang Zhang, Kai Zhao, Tian Wu, Geying Yang, Lina Wang, Run Wang

AAAI 2026 · Federated learning and privacy › Privacy attacks and secure learning · approach: Encryption-based private learning · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use partition-and-combination of Softmax and GeLU instead of CipherPrune pruningprivate BERT inference · BERT-Large (LAN)end-to-end time (s): 210.9 -> 110.6Improved
use partition-and-combination instead of CipherPruneprivate BERT inference · BERT-Large (LAN)communication (GB): 25.3 -> 13.2Improved
use PCFormer instead of Boltprivate BERT inference · BERT-Base (LAN)end-to-end time (s): 260.5 -> 62.2Improved
use PCFormer instead of Bolt or CipherPruneBERT-Base · MNLI/QNLI/SST-2/MRPCaccuracy: MNLI 84.73 vs 84.71 (Bolt)No clear effect
apply partition and combination to ReLU structurelinear-nonlinear block · ReLUtotal latency (ms): 774.3 -> 257.1Improved
apply partition and combination to SiLU structurelinear-nonlinear block · SiLUtotal latency (ms): 3950.5 -> 1033.3Improved
raise token sparsity weight lambda_tok above 0.05 (ablation)PCFormer fine-tuning · BERT-BaseaccuracyHurt
keep lambda_tok and lambda_chn below 0.05 (ablation)PCFormer fine-tuning · BERT-BaseaccuracyNo clear effect
vary token sparsity versus channel sparsity (ablation)PCFormer fine-tuning · BERT-BaseaccuracyMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy