- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposed a transfer learning method that uses adaptive transfer weights since source distributions may change over time. The proposed method combines a target-only predictor and multiple source-specific transfer predictors.
Critical strengths
1.The paper is easy to follow.
- The problem of transfer learning unders shifting source reliability is of great importance.
Critical weaknesses
-
It seems that the weight update does not affect the result of Corollary 1. In the proof, the bound holds for any weights as long as they sum to one. A second point to note is that the last term on the RHS OF the inequlity is somehow large. For example, when T = 20, δ = 0.05 the term is around 4*B (if you use , then 4B is about 9.2) while cumulative loss is approximatey around 9 in Table 9.
-
The baseline parameters are not consistent across methods. For example, Flat-FS and AMTL use different values of and . So the conclusion may be affected by the those parameters. Can the authors provide any insight of how the hyperparameters were chosen? A sensitivity analysis is needed before making the conlusion the .
-
Also, in the theory, it uses ($q_1 = 1/2, \alpha_o = 1/T, c_\lambda ≥ 2\sqrt{2}\nu), but in the experiments, it uses (0.8, 0.025, c_λ = 0.10). Can the authors explain the gap between the theory and the experiments?
-
The real data anaysis has fixed source reliability, which is different than the paper's asscumption on shiting source reliabilities. The hospital sources are fixed. In CIFAR the sources are fixed and the target shifts. On the heart disease data, the proposed AMTL has cumulative loss 5.98 vs SafePool is 6.05. The different seems not statistically significant. In Figure 4b, it shows the transfer weight moving from 0.8 to about 0.65 after 12 batches, so the result may mostly reflect . The results on the 123 held-out records are not reported.
-
Related work is incomplete. What about the paper BOTL (McKay et al., 2020),Ge et al. (2013, 2014)? In addition, model-averaging transfer (Hu and Zhang, 2023) and robust transfer with unreliable sources (Fan et al., 2025) address the same source-weighting question offline. The online transfer methods cited in the introduction (Zhao et al. 2014; Wu et al. 2017; Du et al. 2019; Xie and Pratama 2022) are not compared to the proposed method. Is there a specific reason not doing so? Also, Credit-TL and SafePool have no citation when first mentioned.
Questions for authors
-
Please address the 5 comments list in the weaknesses.
-
How does AMTL compare with re-scoring each source on the target history whenever a snapshot is replaced?
-
Can the authors provide any insight on fixing instead of letting it grow with ?
2 comments
Response to Reviewer aHDX (2/2)
W5. We expanded the Introduction and added HomOTLMS [1], BOTL-OLS based on [2], and TAB based on [4]. They cover online multi-source classification, weighting from target history, and robust source use. Appendix B.3 gives the binary snapshot adaptations and shared batch-feedback protocol.
HomOTLMS extends the single-source setting of Zhao et al. [3], using a passive-aggressive target learner and Hedge weights. BOTL-OLS fits combination weights from current-model predictions on target history. TAB uses its target-boundary decision rule.
The related-work discussion includes local source weighting and prediction consistency [5, 6], continuous-response model averaging [7], domain-stream ensembles [8], and unlabeled-target representation learning [9]. Credit-TL and SafePool are component baselines defined in this study. Section 5.2 identifies them as such, and Appendix B.3 gives their updates and tuning rules.
Q1. We address the five weaknesses in responses W1–W5 above.
Q2. The Source score control in Appendix B.2 scores each source-only model on the observed target history at replacement, using that score for all its strength candidates. AMTL scores each source–strength candidate by cross-fitting. Both retain the Target weight and total transfer mass and select rates on the same validation streams.
Table 8 reports paired AMTL-minus-Source-score losses of , , and in Flip, Rotate, and Switch under the main configuration. It also includes uniform reset. Table 2 compares refresh with inherited weights.
Q3. The revised method fits several strengths and adapts their weights. Appendix A.5 gives the sample-size dependence through Eq. (26):
For an aligned source, the variance-minimizing fraction increases with target history. Source discrepancy adds the bias term in Eq. (25). The candidate library lets different sources and rounds favor different strengths, with the finite-grid variance effect quantified by this identity. Corollary 1 gives the aligned-source rate.
References
[1] Q. Wu, H. Wu, X. Zhou, M. Tan, Y. Xu, Y. Yan, and T. Hao. Online transfer learning with multiple homogeneous or heterogeneous sources. IEEE Transactions on Knowledge and Data Engineering, 29(7):1494–1507, 2017.
[2] H. McKay, N. Griffiths, P. Taylor, T. Damoulas, and Z. Xu. Bi-directional online transfer learning: a framework. Annals of Telecommunications, 75:523–547, 2020.
[3] P. Zhao, S. C. H. Hoi, J. Wang, and B. Li. Online transfer learning. Artificial Intelligence, 216:76–102, 2014.
[4] J. Fan, C. Gao, and J. M. Klusowski. Robust transfer learning with unreliable source data. The Annals of Statistics, 53(4):1728–1752, 2025.
[5] L. Ge, J. Gao, and A. Zhang. OMS-TL: a framework of online multiple source transfer learning. In Proceedings of the 22nd ACM International Conference on Information and Knowledge Management, pp. 2423–2428, 2013.
[6] L. Ge, J. Gao, H. Ngo, K. Li, and A. Zhang. On handling negative transfer and imbalanced distributions in multiple source transfer learning. Statistical Analysis and Data Mining, 7(4):254–271, 2014.
[7] X. Hu and X. Zhang. Optimal parameter-transfer learning by semiparametric model averaging. Journal of Machine Learning Research, 24(358):1–53, 2023.
[8] H. Du, L. L. Minku, and H. Zhou. Multi-source transfer learning for non-stationary environments. In International Joint Conference on Neural Networks, 2019.
[9] R. Xie and M. Pratama. Automatic online multi-source domain adaptation. Information Sciences, 582:480–494, 2022.
Response to Reviewer aHDX (1/2)
W1. Thank you for pointing this out. We now state the general convex-weight result and the bound using AMTL's updates separately. The former is Corollary 3 in Appendix A.7. The main-text Corollary 2 combines Theorem 1 with candidate estimation bounds and includes ∑t=1TEst,t−logΠ(s1:T), which depends on the realized transition and comparison path.
For batch-mean loss, the fluctuation term is now
B21logδ1∑t=1Tbt1.
With equal batch sizes b, it becomes BTlog(1/δ)/(2b), reducing the former batch-level term by 1/b under the same probability allocation. Appendices A.7–A.8 give the conditional within-batch calculation and the resulting path bound.
W2. All main comparisons select parameters by cumulative log loss on shared validation data, separately for each setting. Appendices B.1 and B.3 give the synthetic grids, settings, and baseline implementations. Appendices C–D give the image and hospital protocols. Matched Flat retains AMTL's models and initialization, while independently tuned Flat uses the same full search budget as AMTL. Figure 5 gives initialization and sharing-rate profiles, and Table 2 reports the transition comparison.
W3. Section 4.1 gives the comparison for the executed initialization:
∑t=1Tℓt(pt)−ℓR,t≤−log(1−q1)+(T−1)log1−αo1.
The constant log2+1 uses q1=1/2, αo=1/T, and T≥2. The actual cost is approximately 12.111 in Near, 11.513 in six other settings, and 10−5 in Opposite. The reference is AMTL's internal Target at the same penalty scale.
Theorem 1 applies to the executed parameters. Theorem 2 requires its stated penalty, score, curvature, and localization conditions. Appendix B.1 gives the empirical scales and validation protocol. Table 16 also reports the theory-initialization control, fixing q1=1/2 and αo=1/T, retaining the selected fits and choosing αs on validation data.
W4. We added experiments with changing source snapshots and retained the original target-color and cold-start tasks separately. In Section 5.4, the CIFAR-10 target rule and labels stay fixed while three source snapshots change color rules over five phases. AMTL's cumulative loss is 1.449±0.040, compared with 1.528±0.100 for Target. Table 10 reports all methods and held-out test losses.
The hospital experiment preserves labels while changing source composition through younger patients, older patients, the full cohort, and younger patients again. The warm-start protocol uses 60 calibration records followed by 120 scored Cleveland records. The cold-start protocol scores 180 records. Both reserve 123 records for testing, and validation uses only external hospitals with Cleveland excluded.
Section 5.5 reports warm-start online losses of 3.657±0.072 and 3.696±0.070, the lowest means among the 11 main methods. We report paired comparisons with the strongest baselines; these intervals include zero. Tables 14–15 provide held-out test loss, AUC, and the cold-start comparisons. Figure 3 separates total candidate mass, conditional source weights, and nominal source-objective weight.