Pith. sign in

REVIEW 4 cited by

Sparse Training of Discrete Diffusion Models for Graph Generation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.02142 v2 pith:4OFOPETL submitted 2023-11-03 cs.LG cs.AI

classification cs.LGcs.AI
keywords edgesgraphmodelsgraphslargesparsesparsediffacross
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Generative graph models struggle to scale due to the need to predict the existence or type of edges between all node pairs. To address the resulting quadratic complexity, existing scalable models often impose restrictive assumptions such as a cluster structure within graphs, thus limiting their applicability. To address this, we introduce SparseDiff, a novel diffusion model based on the observation that almost all large graphs are sparse. By selecting a subset of edges, SparseDiff effectively leverages sparse graph representations both during the noising process and within the denoising network, which ensures that space complexity scales linearly with the number of chosen edges. During inference, SparseDiff progressively fills the adjacency matrix with the selected subsets of edges, mirroring the training process. Our model demonstrates state-of-the-art performance across multiple metrics on both small and large datasets, confirming its effectiveness and robustness across varying graph sizes. It also ensures faster convergence, particularly on larger graphs, achieving a fourfold speedup on the large Ego dataset compared to dense models, thereby paving the way for broader applications.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. SynCircuit: Automated Generation of New Synthetic RTL Circuits Can Enable Big Data in Circuits

    cs.LG 2025-08 conditional novelty 6.0 of 10

    SynCircuit generates new, structurally valid RTL circuits with a directed-cyclic-graph diffusion model plus post-processing and MCTS, and shows they improve ML-based PPA prediction when added to training data.

  2. Discrete State Diffusion Models: A Sample Complexity Perspective

    cs.LG 2025-10 reject novelty 5.0 of 10

    Claims the first Õ(ε⁻²) sample-complexity bound for discrete-state diffusion, but the zero-approximation-error, optimization-error, and hardness lemmas carrying the proof are internally broken.

  3. Discrete Diffusion Models: A Unified Framework from Tokenization to Generation

    cs.LG 2026-07 unverdicted novelty 4.0 of 10

    Discrete diffusion models are re-framed as instances of a tokenization-centric, four-component design space (corruption, denoiser, objective, sampler) in a broad survey with no new experimental or theoretical results.

  4. Built Environment Reasoning from Remote Sensing Imagery Using Large Vision--Language Models

    cs.CL 2026-05 unverdicted novelty 3.0 of 10

    Large vision-language models applied to multi-scale remote sensing imagery can generate recommendations on built environment design, constructability, land use, and risks for smart city decision-making.

Pith tools