Pith. sign in

REVIEW 8 cited by

DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion

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 2301.09474 v4 pith:2EFNAYL4 submitted 2023-01-23 cs.LG cs.AI

classification cs.LGcs.AI
keywords diffusioninstanceconstrainedenergyinstanceslearningstructuresclassification
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Real-world data generation often involves complex inter-dependencies among instances, violating the IID-data hypothesis of standard learning paradigms and posing a challenge for uncovering the geometric structures for learning desired instance representations. To this end, we introduce an energy constrained diffusion model which encodes a batch of instances from a dataset into evolutionary states that progressively incorporate other instances' information by their interactions. The diffusion process is constrained by descent criteria w.r.t.~a principled energy function that characterizes the global consistency of instance representations over latent structures. We provide rigorous theory that implies closed-form optimal estimates for the pairwise diffusion strength among arbitrary instance pairs, which gives rise to a new class of neural encoders, dubbed as DIFFormer (diffusion-based Transformers), with two instantiations: a simple version with linear complexity for prohibitive instance numbers, and an advanced version for learning complex structures. Experiments highlight the wide applicability of our model as a general-purpose encoder backbone with superior performance in various tasks, such as node classification on large graphs, semi-supervised image/text classification, and spatial-temporal dynamics prediction.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

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

  1. TRACE: Learning to Compute on Circuit Graphs

    cs.AI 2025-09 conditional novelty 6.0 of 10

    A per-operator hierarchical Transformer with a residual function shift objective substantially improves learning functional behavior of circuit graphs.

  2. Predicting Large-scale Urban Network Dynamics with Energy-informed Graph Neural Diffusion

    cs.LG 2025-07 conditional novelty 6.0 of 10

    A scalable spatiotemporal Transformer, ScaleSTF, matches the accuracy of much larger models on city-scale forecasting tasks at a fraction of the compute and memory cost.

  3. SFi-Former: Sparse Flow Induced Attention for Graph Transformer

    cs.LG 2025-04 conditional novelty 6.0 of 10

    SFi-Former replaces dense graph transformer attention with sparse flows from an l1-regularized energy minimization, improving long-range graph benchmark accuracy and generalization.

  4. Hgformer: Hyperbolic Graph Transformer for Recommendation

    cs.IR 2024-12 reject novelty 6.0 of 10

    Hgformer is a hyperbolic graph transformer for collaborative filtering that reports improved recall and NDCG on six datasets, but its linear-attention approximation is not actually unbiased as claimed.

  5. Even Sparser Graph Transformers

    cs.LG 2024-11 conditional novelty 6.0 of 10

    Spexphormer trains a narrow graph transformer to identify important attention edges, then trains a wider model on the sparsified graph, achieving competitive accuracy with far less memory.

  6. OpenGT: A Comprehensive Benchmark For Graph Transformers

    cs.LG 2025-06 conditional novelty 5.0 of 10

    OpenGT benchmarks 16 graph models on 14 datasets, finding graph transformers excel on heterophilous graphs, though several observations are not robustly supported.

  7. Graph Fourier Transformer with Structure-Frequency Information

    cs.LG 2025-04 conditional novelty 5.0 of 10

    A graph transformer with a fixed spectral-frequency mask on attention reports top scores on five TU datasets, while underperforming several baselines on PATTERN and CLUSTER.

  8. A Theory for Compressibility of Graph Transformers for Transductive Learning

    cs.LG 2024-11 conditional novelty 4.0 of 10

    Under norm, low-rank, or clustering assumptions, a graph transformer's hidden dimension can be compressed with only small error in outputs and attention scores.

Pith tools