SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.14416 · 2020

Improved Knowledge Distillation via Full Kernel Matrix Transfer

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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 5 have no contract verdict; 1 failure of our instrument; 0 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/2009.14416.json · badge: /api/ran/2009.14416.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
idstcv/kda canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
idstcv/kda/main_kda.py
code served (permissive licence) · get_code("131a82fd65128218")
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) and returned list, 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

torch.manual_seed(0)

# Create small tensors for testing
batch_size = 2
num_classes = 4

# output: logits/scores tensor of shape (batch_size, num_classes)
output = torch.randn(batch_size, num_classes)

# target: class indices tensor of shape (batch_size,)
target = torch.tensor([1, 3])

# topk: tuple of k values to compute accuracy for
topk = (1, 2)

ARGS = {
    "output": output,
    "target": target,
    "topk": topk,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list 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
resnet18 Ran
ran on a synthesized input
idstcv/kda/resnet_cifar.py
code served (permissive licence) · get_code("611ab0db5344681b")
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 ResNet. 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 torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "num_classes": 100
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
resnet34 Ran
ran on a synthesized input
idstcv/kda/resnet_cifar.py
code served (permissive licence) · get_code("5ad4d4f85b904e35")
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 ResNet. 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 torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "num_classes": 100
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
resnet50 Ran
ran on a synthesized input
idstcv/kda/resnet_cifar.py
code served (permissive licence) · get_code("c2e0ae17093793fa")
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 ResNet. 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 torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "num_classes": 100
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
train Ran
ran on a synthesized input
idstcv/kda/main_kda.py
code served (permissive licence) · get_code("f5802bd2a5722722")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch.nn as nn
import torch.optim as optim

torch.manual_seed(0)

# Define minimal model that returns (features, logits)
class SimpleModel(nn.Module):
    def __init__(self, num_classes=10):
        super().__init__()
        self.fc1 = nn.Linear(4, 8)
        self.fc2 = nn.Linear(8, num_classes)
        self.feat_dim = 8
    
    def forward(self, x):
        feat = self.fc1(x)
        logits = self.fc2(feat)
        return feat, logits

# Define teacher model (same structure)
class TeacherModel(nn.Module):
    def __init__(self, num_classes=10):
        super().__init__()
        self.fc1 = nn.Linear(4, 8)
        self.fc2 = nn.Linear(8, num_classes)
        self.feat_dim = 8
    
    def forward(self, x):
        feat = self.fc1(x)
        logits = self.fc2(feat)
        return feat, logits

# Criterion functions
criterion = nn.CrossEntropyLoss()

# KDA criterion - simple stand-in that computes MSE between features
class KDACriterion(nn.Module):
    def forward(self, s_feat, t_feat, s_center, t_center):
        return torch.nn.functional.mse_loss(s_feat, t_feat)

criterion_kda = KDACriterion()

# Create dummy train loader - list of (input, target) tuples
train_loader = [
    (torch.randn(2, 4), torch.randint(0, 10, (2,)))
    for _ in range(3)
]

# Create models and optimizer
model = SimpleModel(num_classes=10)
teacher = TeacherModel(num_classes=10)
optimizer = optim.SGD(model.parameters(), lr=0.01)

# Args object
class Args:
    def __init__(self):
        self.cuda = False
        self.warm = 1
        self.epochs = 2
        self.lr = 0.01
        self.alpha = 0.5

args = Args()

# Center tensors and class count
num_classes = 10
feat_dim = 8
t_center = torch.randn(num_classes, feat_dim)
s_center = torch.randn(num_classes, feat_dim)
cN = torch.zeros(num_classes)

ARGS = {
    'train_loader': train_loader,
    'model': model,
    'teacher': teacher,
    'criterion': criterion,
    'criterion_kda': criterion_kda,
    'optimizer': optimizer,
    'epoch': 0,
    'args': args,
    't_center': t_center,
    's_center': s_center,
    'cN': cN,
}
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
validate Ran
ran on a synthesized input
idstcv/kda/main_kda.py
code served (permissive licence) · get_code("c680d9099214f2fb")
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 1, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch.nn as nn
import time

torch.manual_seed(0)

# Build a minimal model that returns (_, output) tuple
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 10)
    
    def forward(self, x):
        output = self.linear(x)
        return None, output

# Create a minimal val_loader: list of (input, target) tuples
val_loader = [
    (torch.randn(2, 4), torch.randint(0, 10, (2,))),
    (torch.randn(2, 4), torch.randint(0, 10, (2,))),
    (torch.randn(2, 4), torch.randint(0, 10, (2,))),
]

# Create the model
model = MinimalModel()

# Create args object with required attributes
class Args:
    def __init__(self):
        self.cuda = False
        self.print_freq = 1

args = Args()

ARGS = {
    'val_loader': val_loader,
    'model': model,
    'args': args
}
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, ndim 1, 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

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 5 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
accuracy 116 other papers
9 dated earlier, 1 the same month, 106 later · 8 only as an assembly brick
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1610.05820 (2016-10)
Membership Inference Attacks Against Machine Learning Models
1905.03696 (2019-05)
HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision
and 113 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

Knowledge distillation is an effective way for model compression in deep learning. Given a large model (i.e., teacher model), it aims to improve the performance of a compact model (i.e., student model) by transferring the information from the teacher. Various information for distillation has been studied. Recently, a number of works propose to transfer the pairwise similarity between examples to distill relative information. However, most of efforts are devoted to developing different similarity measurements, while only a small matrix consisting of examples within a mini-batch is transferred at each iteration that can be inefficient for optimizing the pairwise similarity over the whole data set. In this work, we aim to transfer the full similarity matrix effectively. The main challenge is from the size of the full matrix that is quadratic to the number of examples. To address the challenge, we decompose the original full matrix with Nystr{ö}m method. By selecting appropriate landmark points, our theoretical analysis indicates that the loss for transfer can be further simplified. Concretely, we find that the difference between the original full kernel matrices between teacher and student can be well bounded by that of the corresponding partial matrices, which only consists of similarities between original examples and landmark points. Compared with the full matrix, the size of the partial matrix is linear in the number of examples, which improves the efficiency of optimization significantly. The empirical study on benchmark data sets demonstrates the effectiveness of the proposed algorithm. Code is available at \url{https://github.com/idstcv/KDA}.

For agents

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

get_harvested_code_for_paper("2009.14416")
get_code_for_paper("2009.14416")
have("2009.14416")

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

curl https://syntology.ai/api/ran/2009.14416.json

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

[![Syntology run record](https://syntology.ai/api/ran/2009.14416.svg)](https://syntology.ai/paper/2009.14416)

Connect an agent — have() is free.