SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.20283 · 2026

FastPFRec: A Fast Personalized Federated Recommendation with Secure Sharing ⋆

Jidong Yuan, Haiyang Liu, Zhenxing Yan, Yongqi Sun, Zhihui Gao

arXiv · PDF · Open in the Atlas

Code that ran

8 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 4 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2603.20283.json · badge: /api/ran/2603.20283.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
yanzhenxing123/FastPFRec canonical (classifier label)
classifier basis: census
8 ran · 4 no recorded run
FunctionStatusWhere it lives
FedAvg Ran
ran; our contract draft was wrong, not the code
yanzhenxing123/FastPFRec/model/graph/PerFedRec.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from chandra2thapa/SplitFed-When-Federated-Learning-Meets-Split-Learning, is pointer only (licence: NONE) · get_code("cddf6b6e878cc6ae")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from chandra2thapa/SplitFed-When-Federated-Learning-Meets-Split-Learning, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

FedAvg Ran
ran; our contract draft was wrong, not the code
yanzhenxing123/FastPFRec/model/graph/FastPFRec.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from hongshenghu/source-inference-fl, is pointer only (licence: NONE) · get_code("f9964d719c5cb8f4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from hongshenghu/source-inference-fl, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

FedReAvg Ran
ran; our contract draft was wrong, not the code
yanzhenxing123/FastPFRec/model/graph/PerFedRec.py
code served (permissive licence) · get_code("3d314e0759f77cb6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import copy

torch.manual_seed(0)

# The function expects:
# - w: a list of dicts, where each dict maps keys to tensors
# - N_client: an integer representing the number of clients

# Create sample model state dicts (what w[0], w[1], etc. would be)
# These represent weights from different clients
client_state_1 = {
    'layer1.weight': torch.randn(4, 3),
    'layer1.bias': torch.randn(4),
    'layer2.weight': torch.randn(5, 4),
}

client_state_2 = {
    'layer1.weight': torch.randn(4, 3),
    'layer1.bias': torch.randn(4),
    'layer2.weight': torch.randn(5, 4),
}

client_state_3 = {
    'layer1.weight': torch.randn(4, 3),
    'layer1.bias': torch.randn(4),
    'layer2.weight': torch.randn(5, 4),
}

# Create the list of client weights
w = [client_state_1, client_state_2, client_state_3]

# Number of clients
N_client = 3

ARGS = {
    'w': w,
    'N_client': N_client,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
bpr_loss Ran
ran; our contract draft was wrong, not the code
yanzhenxing123/FastPFRec/util/loss_torch.py
code served (permissive licence) · get_code("cde07004ee483dbc")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function expects three embedding tensors:
# - user_emb: user embeddings, shape (batch_size, embedding_dim)
# - pos_item_emb: positive item embeddings, shape (batch_size, embedding_dim)
# - neg_item_emb: negative item embeddings, shape (batch_size, embedding_dim)
#
# The function performs element-wise multiplication and sum reduction,
# so all three tensors need matching shapes.

batch_size = 2
embedding_dim = 4

user_emb = torch.randn(batch_size, embedding_dim)
pos_item_emb = torch.randn(batch_size, embedding_dim)
neg_item_emb = torch.randn(batch_size, embedding_dim)

ARGS = {
    "user_emb": user_emb,
    "pos_item_emb": pos_item_emb,
    "neg_item_emb": neg_item_emb,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
common Ran
ran, honoured the contract we drafted
yanzhenxing123/FastPFRec/util/algorithm.py
code served (permissive licence) · get_code("e1222a969e6ed9c0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# The function takes two arguments x1 and x2
# It checks where both are non-zero, filters both by that mask, and returns the filtered pair
# x1 and x2 should be tensors or arrays that support:
# - != operator (comparison)
# - & operator (bitwise and)
# - indexing with boolean mask

x1 = torch.tensor([1, 0, 3, 4], dtype=torch.float32)
x2 = torch.tensor([2, 5, 0, 6], dtype=torch.float32)

ARGS = {
    "x1": x1,
    "x2": x2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
l1 Ran
ran, honoured the contract we drafted
yanzhenxing123/FastPFRec/util/algorithm.py
code served (permissive licence) · get_code("cddf7c0cf4dae27e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

torch_seed = 0

# x should be an array-like object that numpy.linalg.norm can process
# The function computes the L1 norm (sum of absolute values)
x = np.array([1.0, -2.0, 3.0, -4.0])

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
l2 Ran
ran, honoured the contract we drafted
yanzhenxing123/FastPFRec/util/algorithm.py
code served (permissive licence) · get_code("04b615bf51851196")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

def setup():
    # The l2 function computes the L2 norm of input x using numpy.linalg.norm
    # It expects x to be array-like (numpy array, list, etc.)
    # Create a small numpy array as test input
    x = np.array([1.0, 2.0, 3.0, 4.0])
    
    return x

ARGS = {
    'x': setup()
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
triplet_loss Ran
ran; our contract draft was wrong, not the code
yanzhenxing123/FastPFRec/util/loss_torch.py
code served (permissive licence) · get_code("029e212249aae32c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create small embedding tensors
batch_size = 2
embedding_dim = 4

user_emb = torch.randn(batch_size, embedding_dim)
pos_item_emb = torch.randn(batch_size, embedding_dim)
neg_item_emb = torch.randn(batch_size, embedding_dim)

ARGS = {
    'user_emb': user_emb,
    'pos_item_emb': pos_item_emb,
    'neg_item_emb': neg_item_emb
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
InfoNCE Not yet run
unverified (harvested, no recorded run)
yanzhenxing123/FastPFRec/util/loss_tf.py
code served (permissive licence) · get_code("73cee5051148c668")
How it ran

no invocation recorded.

bpr_loss Not yet run
unverified (harvested, no recorded run)
yanzhenxing123/FastPFRec/util/loss_tf.py
code served (permissive licence) · get_code("9325c22d0eb06da3")
How it ran

no invocation recorded.

l2_reg_loss Not yet run
unverified (harvested, no recorded run)
yanzhenxing123/FastPFRec/util/loss_torch.py
code served (permissive licence) · get_code("c75b86662f8dec6b")
How it ran

no invocation recorded.

ssm_loss Not yet run
unverified (harvested, no recorded run)
yanzhenxing123/FastPFRec/util/loss_tf.py
code served (permissive licence) · get_code("517a13a2d3646e6f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 10 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 0 the same month, 0 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
FedAvg 9 other papers
9 dated earlier
1602.05629 (2016-02)
Communication-Efficient Learning of Deep Networks from Decentralized Data
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
1812.07108 (2018-12)
Learning Private Neural Language Modeling with Attentive Aggregation
and 6 more not named here
common 3 other papers
3 dated earlier
2401.01527 (2024-01)
Poisoning Attacks against Recommender Systems: A Survey
2403.04287 (2024-03)
DGR: A General Graph Desmoothing Framework for Recommendation via Global and Local Perspectives
2405.00287 (2024-05)
SCONE: A Novel Stochastic Sampling to Generate Contrastive Views and Hard Negative Samples for Recommendation
l1 3 other papers
3 dated earlier
2401.01527 (2024-01)
Poisoning Attacks against Recommender Systems: A Survey
2403.04287 (2024-03)
DGR: A General Graph Desmoothing Framework for Recommendation via Global and Local Perspectives
2405.00287 (2024-05)
SCONE: A Novel Stochastic Sampling to Generate Contrastive Views and Hard Negative Samples for Recommendation
l2 3 other papers
3 dated earlier
2401.01527 (2024-01)
Poisoning Attacks against Recommender Systems: A Survey
2403.04287 (2024-03)
DGR: A General Graph Desmoothing Framework for Recommendation via Global and Local Perspectives
2405.00287 (2024-05)
SCONE: A Novel Stochastic Sampling to Generate Contrastive Views and Hard Negative Samples for Recommendation
InfoNCE 2 other papers
2 dated earlier
2403.04287 (2024-03)
DGR: A General Graph Desmoothing Framework for Recommendation via Global and Local Perspectives
2405.00287 (2024-05)
SCONE: A Novel Stochastic Sampling to Generate Contrastive Views and Hard Negative Samples for Recommendation
bpr_loss 2 other papers
2 dated earlier
2403.04287 (2024-03)
DGR: A General Graph Desmoothing Framework for Recommendation via Global and Local Perspectives
2405.00287 (2024-05)
SCONE: A Novel Stochastic Sampling to Generate Contrastive Views and Hard Negative Samples for Recommendation
bpr_loss 2 other papers
2 dated earlier
2403.04287 (2024-03)
DGR: A General Graph Desmoothing Framework for Recommendation via Global and Local Perspectives
2405.00287 (2024-05)
SCONE: A Novel Stochastic Sampling to Generate Contrastive Views and Hard Negative Samples for Recommendation
l2_reg_loss 2 other papers
2 dated earlier
2403.04287 (2024-03)
DGR: A General Graph Desmoothing Framework for Recommendation via Global and Local Perspectives
2405.00287 (2024-05)
SCONE: A Novel Stochastic Sampling to Generate Contrastive Views and Hard Negative Samples for Recommendation
ssm_loss 2 other papers
2 dated earlier
2403.04287 (2024-03)
DGR: A General Graph Desmoothing Framework for Recommendation via Global and Local Perspectives
2405.00287 (2024-05)
SCONE: A Novel Stochastic Sampling to Generate Contrastive Views and Hard Negative Samples for Recommendation
triplet_loss 2 other papers
2 dated earlier
2403.04287 (2024-03)
DGR: A General Graph Desmoothing Framework for Recommendation via Global and Local Perspectives
2405.00287 (2024-05)
SCONE: A Novel Stochastic Sampling to Generate Contrastive Views and Hard Negative Samples for Recommendation

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Graph neural network (GNN)-based federated recommendation systems effectively capture user-item relationships while preserving data privacy. However, existing methods often face slow convergence on graph data and privacy leakage risks during collaboration. To address these challenges, we propose FastPFRec (Fast Personalized Federated Recommendation with Secure Sharing), a novel framework that enhances both training efficiency and data security. FastPFRec accelerates model convergence through an efficient local update strategy and introduces a privacy-aware parameter sharing mechanism to mitigate leakage risks. Experiments on four real-world datasets (Yelp, Kindle, Gowalla-100k, and Gowalla-1m) show that FastPFRec achieves 32.0% fewer training rounds, 34.1% shorter training time, and 8.1% higher accuracy compared with existing baselines. These results demonstrate that FastPFRec provides an efficient and privacy-preserving solution for scalable federated recommendation.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2603.20283")
get_code_for_paper("2603.20283")
have("2603.20283")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2603.20283.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2603.20283.svg)](https://syntology.ai/paper/2603.20283)

Connect an agent — have() is free.