SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.02129 · 2022

Decentralized Hyper-Gradient Computation over Time-Varying Directed Networks

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2210.02129.json · badge: /api/ran/2210.02129.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
hitachi-rd-cv/pdbo-hgp canonical (classifier label)
classifier basis not recorded on the link
2 ran · 2 no recorded run
FunctionStatusWhere it lives
kron_matrix_vector_prod Ran
ran on a synthesized input
hitachi-rd-cv/pdbo-hgp/lib_task/concat_hgp.py
code served (permissive licence) · get_code("d6e100d883d31bd3")
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 1, dtype family float, shape (8,) 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)

# Construct valid arguments for kron_matrix_vector_prod
# The function expects:
# - v: a vector that will be reshaped to (A.shape[1], -1)
# - A: a matrix that will be used in matrix multiplication A @ V
# - B: optional (not implemented)

# Let's say A has shape (4, 3)
# Then V will be reshaped to (3, -1), so v should have 3*k elements for some k
# Let's use k=2, so v has 6 elements total

A = torch.randn(4, 3)  # 4x3 matrix
v = torch.randn(6)     # 6 elements: will reshape to (3, 2)

ARGS = {
    "v": v,
    "A": A,
    "B": None
}
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 1, dtype family float, shape (8,) — shape (8,) 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
split_params_and_weights Ran
ran on a synthesized input
hitachi-rd-cv/pdbo-hgp/lib_task/concat_hgp.py
code served (permissive licence) · get_code("a0a9e1c53865bfb9")
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. 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

torch.manual_seed(0)

# Construct arguments for split_params_and_weights
# The function takes:
# - param_weight_cat: a flattened tensor of parameters and weights concatenated
# - n_nodes: number of nodes

# Let's create a tensor that will be reshaped to (n_nodes, -1)
# where the last column is weights and the rest are params_biased
# Using distinct dimensions: n_nodes=3, features_per_node=5 (4 params + 1 weight)
n_nodes = 3
features_per_node = 5

# Create a tensor of shape (n_nodes * features_per_node,) = (15,)
param_weight_cat = torch.randn(n_nodes * features_per_node)

ARGS = {
    "param_weight_cat": param_weight_cat,
    "n_nodes": n_nodes,
}
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 tuple — a tuple output has no array shape of its own; none is 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
concat_params_and_weights Not yet run
unverified (harvested, no recorded run)
hitachi-rd-cv/pdbo-hgp/lib_task/concat_hgp.py
code served (permissive licence) · get_code("686751f3ff396a2a")
How it ran

no invocation recorded.

get_mobilenet Not yet run
unverified (harvested, no recorded run)
hitachi-rd-cv/pdbo-hgp/fedem/models.py
code served (permissive licence) · get_code("9c1e58d7bca6b6c9")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 3 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
get_mobilenet 4 other papers
1 dated earlier, 3 later
2108.10252 (2021-08)
Federated Multi-Task Learning under a Mixture of Distributions
2301.04632 (2023-01)
Federated Learning under Heterogeneous and Correlated Client Availability
2305.01068 (2023-05)
Personalized Federated Learning under Mixture of Distributions
and 1 more not named here

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

This paper addresses the communication issues when estimating hyper-gradients in decentralized federated learning (FL). Hyper-gradients in decentralized FL quantifies how the performance of globally shared optimal model is influenced by the perturbations in clients' hyper-parameters. In prior work, clients trace this influence through the communication of Hessian matrices over a static undirected network, resulting in (i) excessive communication costs and (ii) inability to make use of more efficient and robust networks, namely, time-varying directed networks. To solve these issues, we introduce an alternative optimality condition for FL using an averaging operation on model parameters and gradients. We then employ Push-Sum as the averaging operation, which is a consensus optimization technique for time-varying directed networks. As a result, the hyper-gradient estimator derived from our optimality condition enjoys two desirable properties; (i) it only requires Push-Sum communication of vectors and (ii) it can operate over time-varying directed networks. We confirm the convergence of our estimator to the true hyper-gradient both theoretically and empirically, and we further demonstrate that it enables two novel applications: decentralized influence estimation and personalization over time-varying networks.

For agents

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

get_harvested_code_for_paper("2210.02129")
get_code_for_paper("2210.02129")
have("2210.02129")

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

curl https://syntology.ai/api/ran/2210.02129.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.02129.svg)](https://syntology.ai/paper/2210.02129)

Connect an agent — have() is free.