SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.05032 · AAAI · 2023

Online Hyperparameter Optimization for Class-Incremental Learning

Bernt Schiele, Qianru Sun, Yingying Li, Yaoyao Liu

arXiv · PDF · Open in the Atlas

Code that ran

1 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 0 have no contract verdict; 1 failure of our instrument; 3 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/2301.05032.json · badge: /api/ran/2301.05032.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
yaoyao-liu/online-hyperparameter-optimization marked official in Papers with Code
Papers with Code archive
1 ran · 3 no recorded run
FunctionStatusWhere it lives
process_inputs_fp Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yaoyao-liu/online-hyperparameter-optimization/trainer/mixed.py
code served (permissive licence) · get_code("536f0a5a9bb31e78")
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 2, dtype family float, shape (2, 3) 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 as nn

torch.manual_seed(0)

# Build a simple model with multiple layers so we can extract features
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.layer1 = nn.Linear(4, 8)
        self.layer2 = nn.Linear(8, 6)
        self.layer3 = nn.Linear(6, 3)
    
    def forward(self, x):
        x = self.layer1(x)
        x = torch.relu(x)
        x = self.layer2(x)
        x = torch.relu(x)
        x = self.layer3(x)
        return x

# Create model instance
b1_model = SimpleModel()

# Create small input tensor (batch=2, features=4)
inputs = torch.randn(2, 4)

# Create arguments dict
ARGS = {
    "the_args": None,
    "b1_model": b1_model,
    "inputs": inputs,
    "feature_mode": False
}
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 2, dtype family float, shape (2, 3) — shape (2, 3) 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
get_cur_features Not yet run
unverified (harvested, no recorded run)
yaoyao-liu/online-hyperparameter-optimization/trainer/mixed.py
code served (permissive licence) · get_code("64d0fe3892ae383e")
How it ran

no invocation recorded.

get_ref_features Not yet run
unverified (harvested, no recorded run)
yaoyao-liu/online-hyperparameter-optimization/trainer/mixed.py
code served (permissive licence) · get_code("aad6747e4c51a016")
How it ran

no invocation recorded.

incremental_train_and_eval Not yet run
unverified (harvested, no recorded run)
yaoyao-liu/online-hyperparameter-optimization/trainer/mixed.py
code served (permissive licence) · get_code("20a1cbf064795d91")
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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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.

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

Class-incremental learning (CIL) aims to train a classification model while the number of classes increases phase-byphase. An inherent challenge of CIL is the stability-plasticity tradeoff, i.e., CIL models should keep stable to retain old knowledge and keep plastic to absorb new knowledge. However, none of the existing CIL models can achieve the optimal tradeoff in different data-receiving settings-where typically the training-from-half (TFH) setting needs more stability, but the training-from-scratch (TFS) needs more plasticity. To this end, we design an online learning method that can adaptively optimize the tradeoff without knowing the setting as a priori. Specifically, we first introduce the key hyperparameters that influence the tradeoff, e.g., knowledge distillation (KD) loss weights, learning rates, and classifier types. Then, we formulate the hyperparameter optimization process as an online Markov Decision Process (MDP) problem and propose a specific algorithm to solve it. We apply local estimated rewards and a classic bandit algorithm Exp3 to address the issues when applying online MDP methods to the CIL protocol. Our method consistently improves top-performing CIL methods in both TFH and TFS settings, e.g., boosting the average accuracy of TFH and TFS by 2.2 percentage points on ImageNet-Full, compared to the state-of-the-art. Code is provided at https://class-il.mpi-inf.mpg.de/online/

For agents

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

get_harvested_code_for_paper("2301.05032")
get_code_for_paper("2301.05032")
have("2301.05032")

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

curl https://syntology.ai/api/ran/2301.05032.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.05032.svg)](https://syntology.ai/paper/2301.05032)

Connect an agent — have() is free.