- Rating
- 2
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes LBF, a training-order principle for combining complementary information sources in SID–based generative recommendation. The authors observe that readily exploitable signals can dominate early optimization and prevent complementary but harder-to-learn predictors from developing their own structure. They characterize this phenomenon as Training-time Optimization Accessibility (TOA). LBF proposes: establish the lower-TOA complementary predictor first, then introduce higher-TOA signals for refinement, and instantiates this as CVGR$^{2}$.
Critical strengths
S1: The central idea that optimization can prevent complementary pathways from fully emerging if one pathway is too easy early, is plausible.
S2: CVGR$^2$ implements staged learning on both the generation side and the ranking side: on the generation side, it performs dense refinement after the SID predictor; on the ranking side, it fuses history-conditioned relevance before SID-matched evidence.
Critical weaknesses
W1: The idea that training simpler or harder-to-learn tasks before easier ones is well-established in curriculum learning, multi-task learning. Scheduling auxiliary losses or features sequentially is not new. While the application to SID-based recommendation is domain-specific, the fundamental contribution is incremental.
W2: The paper does not provide a specific definition or measurement standard for TOA. At line 1101, it also acknowledges that Eq. (26) is “not as a direct numerical estimator of TOA.” In addition, it does not show that TOA mismatch can explain the gains under different settings. Therefore, it is difficult to determine whether the performance improvement truly comes from the TOA mechanism, rather than from the general benefits of staged training or regularization.
W3: The paper uses GAOQ from ReSID as the quantizer, FAMAE from ReSID to learn item representations, and Node2Vec to learn graph-based representation. However, it does not provide reasons for why these methods are chosen. Also, under other quantizers and representation-learning methods, how does the CVGR$^{2}$ perform?
Questions for authors
see the weaknesses.
2 comments
W2: How Is TOA Defined, and Does It Explain LBF's Gains?
As defined in Section 2.2, Training-time Optimization Accessibility (TOA) describes how readily a model can exploit a given input pathway to reduce training loss under its current optimization state. We treat TOA as a qualitative comparison between pathways rather than a calibrated numerical measure. To examine this property empirically, we independently train SID-only and Graph Dense-only predictors from scratch under the same training configuration to predict the same target SIDs. The table reports the sum of mean token-level negative log-likelihoods (NLLs) on BP at selected epochs.
| Historical input | Epoch 10 | Epoch 50 | Epoch 100 |
|---|---|---|---|
| SID-only | 8.7424 | 8.4087 | 8.2766 |
| Dense-only | 8.6807 | 8.2595 | 8.0182 |
Dense-only yields lower NLL at all three checkpoints, indicating that graph-based dense inputs are more readily used to fit the prediction target under this setup.
To distinguish the benefits of dense refinement from those of continued training, we conducted additional controls on BP. Each strategy continues from its validation-best Stage-1 checkpoint using the same Stage-2 optimization settings as LBF. Early retains dense inputs, SID-only remains unchanged, and LBF introduces graph-based dense refinement.
| Training strategy | Stage 1 R@10 (%) | Stage 2 R@10 (%) |
|---|---|---|
| Early → Early | 4.1715 | 4.0650 |
| SID-only → SID-only | 4.6496 | 4.6656 |
| SID-only → Graph LBF | 4.6496 | 4.7149 |
Continuation alone provides little or no benefit, whereas LBF achieves a clear improvement.
For reranking, we also separated delayed evidence introduction from freezing, using two-stage training under the corresponding configurations:
| Evidence introduction | Stage-2 base ranker | Test R@10 (%) |
|---|---|---|
| Early | Unfrozen | 4.7961 |
| Early | Frozen | 4.8121 |
| Delayed | Unfrozen | 5.0831 |
| Delayed | Frozen | 5.1350 |
Early continues from a history-plus-evidence model, whereas Delayed starts from a history-only model and then introduces decoder evidence. Delayed introduction yields the larger improvement in either freezing condition, suggesting that fusion timing is the main source of the observed difference.
We will clarify TOA's definition, present it as an empirically supported explanation of the training behavior, and incorporate these experiments into the revision.
W3: Does CVGR² Generalize to Other Representations and Quantizers?
Our goal is not to propose a new representation learner or quantizer, but to investigate how different item relationships and their predictive signals can be effectively combined. In the original configuration, FAMAE, Sentence-T5 text embeddings, and Node2Vec capture behavioral/field information, semantic content, and graph-based collaborative relations, respectively. GAOQ provides a unified, reproducible procedure for constructing multi-view SIDs.
To test dependence on these components, we replaced the representation sources and quantizer in additional BP experiments:
| SID representations / quantizer | SID-only G1 | LBF G2 | History-only R1 | Evidence-added R2 |
|---|---|---|---|---|
| FAMAE+Text+Graph / GAOQ | 4.6496 | 4.7149 | 4.4126 | 5.1350 |
| FAMAE+Text+BERT4Rec / GAOQ | 4.7268 | 4.7908 | 4.3520 | 5.1337 |
| BERT4Rec+Text+SASRec / GAOQ | 4.6529 | 4.6702 | 4.3347 | 5.0777 |
| BERT4Rec+Graph+SASRec / GAOQ | 4.4991 | 4.5258 | 4.3659 | 4.9972 |
| FAMAE+Text+Graph / RQKMeans | 4.1928 | 4.2201 | 4.1522 | 4.7029 |
For BERT4Rec and SASRec, we obtain embeddings through training and concatenate item-ID and field embeddings to form item representations. RQKMeans uses three residual KMeans levels with 256 centroids per level, plus a deduplication token. We retrain the generator for each SID configuration.
Across all tested configurations, G2 outperforms G1 and R2 outperforms R1. These results show that CVGR² accommodates different SID representation sources and quantization schemes while retaining the predictive benefits of adding complementary information. We will include the component-selection rationale, implementation details, and replacement results in the paper.
We appreciate the reviewer's thoughtful comments. Below, we provide detailed responses to the concerns, supported by additional experiments.
W1: How Does LBF Differ from Existing Staged Training Methods?
We recognize that staged training and the sequential introduction of auxiliary signals have been explored in prior work. Traditional curriculum learning often orders training examples by difficulty, while staged multi-task learning commonly schedules different tasks. However, our focus is on a specific asymmetry between input pathways within the same prediction task: one pathway may already contain readily exploitable predictive information, while a complementary predictor must still be learned from scratch.
LBF therefore establishes the complementary predictor first, then introduces the readily exploitable signal for refinement, differing from the common easy-to-hard curriculum. In this generative recommendation setting, the representative balancing strategies do not exploit the complementary pathways as effectively as LBF. We compare LBF with several multimodal balancing strategies adapted to our architecture on BP. For reranking, all methods use the same candidate sets generated by the same model.
We implemented the strategies as follows:
LBF achieves the best performance in both stages among the tested strategies. Our contribution is not the general idea of staged training itself, but addressing how to better leverage complementary information in generative recommendation. We propose the CVGR² framework to integrate multiple predictive signals and a simple yet effective LBF strategy to address the resulting fusion training challenges, achieving strong overall performance. We will clarify this contribution and add the related work and experiments to the paper.
[1] Balanced Multimodal Learning via On-the-Fly Gradient Modulation.
[2] Multimodal Representation Learning by Alternating Unimodal Adaptation.
[3] Improving Multi-Modal Learning with Uni-Modal Teachers.