Papers › Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods

Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods

8 Nov 2021ICLR 2022 4arXiv:2111.04840archive 2025-07-28

Wenqing Zheng, Edward W Huang, Nikhil Rao, Sumeet Katariya, Zhangyang Wang, Karthik Subbian

Graph Neural Networks (GNNs) have achieved state-of-the-art performance in node classification, regression, and recommendation tasks. GNNs work well when rich and high-quality connections are available. However, their effectiveness is often jeopardized in many real-world graphs in which node degrees have power-law distributions. The extreme case of this situation, where a node may have no neighbors, is called Strict Cold Start (SCS). SCS forces the prediction to rely completely on the node's own features. We propose Cold Brew, a teacher-student distillation approach to address the SCS and noisy-neighbor challenges for GNNs. We also introduce feature contribution ratio (FCR), a metric to quantify the behavior of inductive GNNs to solve SCS. We experimentally show that FCR disentangles the contributions of different graph data components and helps select the best architecture for SCS generalization. We further demonstrate the superior performance of Cold Brew on several public benchmark and proprietary e-commerce datasets, where many nodes have either very few or noisy connections. Our source code is available at https://github.com/amazon-research/gnn-tail-generalization.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 14 ran (12 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

amazon-research/gnn-tail-generalization officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 16 samples, 14 ran (2 instrument-failed) · 2 unverified report
amazon-science/gnn-tail-generalization mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to arXiv:2310.00800 (its page on Syntology; that paper's own run record: 21 ran (of which 2 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

16 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
1ran · our draft was wrong
1ran; the contract check could not run
11ran
2unverified

Licence: 0 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from amazon-research/gnn-tail-generalization. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

amazon-research/gnn-tail-generalization official repository 16 samples, 14 ran (2 instrument-failed) · 2 unverified
AcontainsB GNN_model/drop_tricks.py ran · violated contract Apache-2.0 (permissive) · 19511295442b8b8a · report fixture: signature A:str/0/str, listB:list/1/str · returned bool · level recorded 2026-09-24
adaptive_auc_loss Link_prediction_model/loss.py ran Apache-2.0 (permissive) · 3cbbe6f92c0de08c · report fixture: signature pos_out:Tensor/1/float, neg_out:Tensor/1/float, num_neg:int/0/int, weight:Tensor/1/float · returned Tensor · level recorded 2026-09-24
auc_loss Link_prediction_model/loss.py ran Apache-2.0 (permissive) · 4b9ae549a5732877 · report fixture: signature pos_out:Tensor/1/float, neg_out:Tensor/1/float, num_neg:int/0/int · returned Tensor · level recorded 2026-09-24
build_edge_adj Link_prediction_model/edge_LP.py ran Apache-2.0 (permissive) · 2859a58982511839 · report fixture: signature edge_index:Tensor/2/int · returned tuple · level recorded 2026-09-24
cal_acc_indices Label_propagation_model/LP_Adj.py ran Apache-2.0 (permissive) · 2c1fff89f9280558 · report fixture: signature output:Tensor/2/float, labels:Tensor/1/int · returned float · level recorded 2026-09-24
cal_acc_logits Label_propagation_model/LP_Adj.py ran Apache-2.0 (permissive) · 4995964ae5fddaf1 · report fixture: signature output:Tensor/2/float, labels:Tensor/1/int · returned float · level recorded 2026-09-24
diffusion in 6 papers Label_propagation_model/diffusion_feature.py ran Apache-2.0 (permissive) · afbdc85089318f81 · report fixture: signature x:ndarray/2/float, adj:csr_matrix/2/float, num_propagations:int/0/int, p:float/0/float, alpha:float/0/float · returned Tensor · level recorded 2026-09-24
gen_normalized_adjs Label_propagation_model/outcome_correlation.py ran Apache-2.0 (permissive) · 8e4eee31155a52fb · report fixture: signature adj:Tensor/2/float, D_isqrt:Tensor/1/float · returned tuple · level recorded 2026-09-24
log_rank_loss Link_prediction_model/loss.py ran Apache-2.0 (permissive) · 03d2b1e423c6445b · report fixture: signature pos_out:Tensor/1/float, neg_out:Tensor/1/float, num_neg:int/0/int · returned Tensor · level recorded 2026-09-24
reset_weight_GroupNorm GNN_model/norm_tricks.py ran · our draft was wrong Apache-2.0 (permissive) · a5483c4f44a5f81a · report fixture: signature args:SimpleArgs/0/? · returned SimpleArgs · level recorded 2026-09-24
run_norm_if_any GNN_model/norm_tricks.py ran Apache-2.0 (permissive) · 429df79768882322 · report fixture: signature net:callable/0/?, x:Tensor/2/float, ilayer:int/0/int · returned Tensor · level recorded 2026-09-24
sgc Label_propagation_model/diffusion_feature.py ran Apache-2.0 (permissive) · a33fe9e4734902f9 · report fixture: signature x:ndarray/2/float, adj:ndarray/2/float, num_propagations:int/0/int · returned Tensor · level recorded 2026-09-24
to_device in 75 papers Label_propagation_model/LP_Adj.py ran Apache-2.0 (permissive) · bfdd8eb94daad37e · report fixture: signature list1d:list/1/dict, device:str/0/str · returned list · level recorded 2026-09-24
tonp in 10 papers GNN_model/GCN.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 18d569c66cbe1eda · report fixture: signature arr:Tensor/2/float · returned ndarray · level recorded 2026-09-24
general_outcome_correlation_YAG Label_propagation_model/outcome_correlation.py unverified Apache-2.0 (permissive) · 1c9f7749bb1f3502 · report
lp Label_propagation_model/diffusion_feature.py unverified Apache-2.0 (permissive) · 869350b6e16a5a33 · report

Tasks

Node Classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections