- Rating
- 4
- Confidence
- 2
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper presents trajectory matching, a novel discrete flow matching approach for tree and graph generation. Trajectory matching gives a comprehensive theoretic framework and practical algorithm to condition generative flow on a full sequence of actions connecting the endpoints. Benchmark experiments on tree and molecular graph generation framework demonstrates the advantages of trajectory matching.
Critical strengths
- This paper makes an excellent theoretic novelty contribution by proposing trajectory matching as an efficient discrete flow matching framework for action sequence generation. Theory formulation and proof are comprehensively presented.
- Empirical experiments on tree and molecular graph generation clearly demonstrate the advantages of trajectory matching with strong experimental results.
Critical weaknesses
- There lacks a discussion and comparation of computational time cost.
- For molecular graph generation, an important practical application is property guided molecular generation, i.e., generating molecules with desired properties. A discussion or experiment about extending trajectory matching to property guided generation is needed.
Questions for authors
No other questions, see "Critical Weaknesses" section.
3 comments
Follow-up Response
I appreciate authors' efforts in rebuttal. My concerns have been addressed so I will keep my rate.
Thank you again for your thoughtful review, fast follow-up and constructive suggestions!
We thank the reviewer for their thoughtful review and positive assessment of our theoretical contribution and empirical results.
Weakness 1: Computational cost.
Computational cost is reported in Appendix G.1, Tables 5–6. The additional computational overhead compared with the factorized DFM baseline DeFoG is modest for training: approximately 11–16% more time per training step on QM9. For sampling, our instantiations require 28–34% more time per generated sample at the same 500-step budget. These overheads do not necessarily translate into higher overall cost: structured actions can enable smaller models and fewer training or sampling steps. For example, on Tree, our smaller model trains in less than 1 hour, compared with approximately 8 hours reported for DeFoG, and maintains 100% validity even at 10 sampling steps. We have made the reference to these measurements more prominent in the main text.
Weakness 2: Property-guided molecular generation.
A benefit of formulating structured-action generation within discrete flow matching is that established conditioning and guidance mechanisms [1] carry over naturally to the learned action rates.
Specifically, we train a conditional rate predictor utθ(s,a∣r), providing the final training molecule’s property value r alongside sampled intermediate states. The trajectory-matching targets and objective remain unchanged. Randomly replacing the condition with a null condition ∅ during training allows the same network to learn conditional and unconditional rates. At generation time, we specify a desired value r⋆ and apply classifier-free guidance:
$u_t^{\theta,w}(s,a\mid r^\star) = \bigl[u_t^\theta(s,a\mid r^\star)\bigr]^w \bigl[u_t^\theta(s,a\mid\varnothing)\bigr]^{1-w}. $
Here, w=0 gives unconditional generation, w=1 uses the conditional model, and w>1 strengthens guidance. These rates are used in the usual sampling procedure.
As an initial experiment, we evaluated logP-conditioned generation on QM9 for AtomGrow and FragGrow:
These initial results show that property guidance enables both instantiations to generate molecules with property values closer to the desired targets. Stronger guidance further improves agreement with these targets while maintaining high validity. We have added the guidance formulation, experimental details, and results to Appendix G.8.
[1] Nisonoff et al. Unlocking Guidance for Discrete State-Space Diffusion and Flow Models. ICLR 2025.