- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper introduces StreamDC, a shared-memory approach to teacher-guided time-series dataset condensation. Instead of storing independently synthesized sequences, the method organizes the same number of signal values into class-specific segments within a concatenated temporal memory.
During synthesis, overlapping linear windows and class-local cyclic windows are jointly optimized through existing condensation objectives. Windows crossing class boundaries receive occupancy-proportional soft targets, while cyclic windows provide additional temporal origins within individual class segments. After synthesis, the memory is decoded at a finer stride, and a student model is trained using teacher predictions on the resulting windows.
Experiments across five datasets, three condensation backends, and two storage budgets evaluate the method against independent synthesis and existing time-series condensation approaches. The results generally favor the complete StreamDC pipeline. Additional experiments examine window design, post-hoc decoding, sample replication, synthesis and decoding strides, and cross-architecture transfer.
Critical strengths
1. A simple and practical approach to reusing a limited synthetic-data budget.
The paper addresses a useful question in time-series dataset condensation: how to expose synthetic signals at different temporal positions without storing additional copies. By organizing the synthetic data into a shared memory and applying overlapping and cyclic readouts, StreamDC separates the amount of stored signal from the number of training windows generated from it. The class-local cyclic readout is particularly useful at very small storage budgets, where ordinary within-class sliding windows offer few distinct temporal origins. The ability to combine this design with several existing condensation objectives makes the approach useful beyond a single backend.
2. A broad empirical evaluation supported by informative controls.
The evaluation across five datasets, three backends, and two storage budgets provides encouraging evidence for the effectiveness of the overall approach. The post-hoc decoding, sample replication, window-family ablations, and stride analyses help identify which aspects of the pipeline contribute to its performance. Although these experiments do not completely separate the effects of synthesis and student training, they provide useful evidence about the importance of the readout design. I view the combination of a simple method, compatibility with multiple backends, and broad empirical improvements as the main reason to support acceptance.
Critical weaknesses
1. Insufficient positioning relative to shared-canvas dataset distillation.
The shared-memory formulation has close connections to existing work on shared-canvas dataset distillation. In particular, PoDD (Shul et al., 2025) already studies distilling data into a shared poster, extracting overlapping crops, and jointly updating the underlying stored values. It also considers class ordering and labeling strategies for the shared layout.
These connections do not invalidate the practical value of adapting the approach to time series. The class-local cyclic readout and the separation of synthesis and decoding strides are relevant design choices in the proposed setting. However, the paper could more clearly distinguish which components build on prior work and which provide additional methodological contributions. A more explicit discussion would help assess the precise extent of the novelty.
2. Incomplete separation of the sources of empirical improvement.
The main comparisons change both the synthesis procedure and the data used for student training. The independent-synthesis baselines in Table 1 also use teacher supervision, but StreamDC provides the student with a larger collection of temporally shifted and cross-class windows. Consequently, the resulting performance gap does not by itself establish how much improvement comes specifically from joint optimization of the shared memory.
The post-hoc decoding control in Table 3 is particularly informative. Applying the StreamDC readout to independently synthesized samples already recovers a substantial part of the improvement. Relative to the reported post-hoc decoding baseline, StreamDC achieves additional gains of 3.37 and 0.51 percentage points on HAR, and 9.56 and 1.78 points on Sleep, at SPC 1 and SPC 5 respectively. These results suggest benefits beyond post-hoc decoding, with their magnitude varying across datasets and storage budgets. More extensive comparisons with matched readout augmentation, teacher supervision, and student optimization budgets would strengthen the interpretation of these gains.
There is a separate difference in student supervision in Table 2: Random, K-center, and TexTSC use hard-label training, while StreamDC uses teacher distillation. These results are useful as comparisons of complete pipelines, but they do not isolate the contribution of the condensed representation itself.
Overall, I lean toward Weak Accept. These concerns mainly affect the attribution and positioning of the contribution. Despite these limitations, I find the overall approach practically useful and the reported improvements across multiple settings encouraging. The simplicity and flexibility of the complete framework provide sufficient value to support acceptance.
Questions for authors
-
Relationship to existing dataset distillation methods. Could the authors clarify the relationship between StreamDC and PoDD, particularly regarding shared storage, overlapping readouts, class ordering, and labeling? Which components constitute additional contributions for time-series condensation? A more explicit distinction would help assess the methodological novelty.
-
Contribution of joint synthesis. Could the authors extend the post-hoc decoding control to representative additional datasets or backends, while matching the readout augmentation, teacher supervision, and student optimization budget? This would help determine whether the additional gains from joint optimization remain consistent beyond the currently reported settings.
-
Comparability of student-training protocols. For Table 2, how would Random and K-center perform when trained with the same teacher supervision and temporal augmentation as StreamDC? It would be helpful to understand whether the main conclusions remain unchanged under a more closely matched training protocol.
-
Role of cyclic windows at different stages. The current cyclic-window ablation changes both synthesis and decoding. Could the authors separately examine the effect of cyclic windows during memory optimization and during student training? This would help clarify whether their benefit primarily comes from improving the learned memory, enriching the training views, or the interaction between the two stages.
2 comments
Response to Reviewer JTN4 (2/2)
A.3. Random/K-center with the same teacher supervision and readout.
Following your suggestion, we gave Random and K-center both the same KL teacher supervision and the same hybrid temporal readout as StreamDC. These directly address whether the advantage persists when selected real examples receive those components too. Accuracy (%) is mean ± standard deviation; StreamDC uses ShapeCond. The final column is its margin over the stronger coreset.
| Dataset | SPC | Random + Hybrid + KL | K-center + Hybrid + KL | StreamDC | Difference |
|---|---|---|---|---|---|
| HAR | 1 | 71.95 ± 5.31 | 78.31 ± 2.29 | 86.35 ± 2.10 | +8.04 |
| HAR | 5 | 92.76 ± 0.91 | 91.63 ± 0.48 | 93.92 ± 0.65 | +1.16 |
| FacesUCR | 1 | 93.07 ± 1.76 | 91.54 ± 1.08 | 93.80 ± 0.54 | +0.73 |
| FacesUCR | 5 | 95.19 ± 0.71 | 95.19 ± 0.78 | 95.40 ± 0.62 | +0.21 |
| Electric | 1 | 59.41 ± 7.70 | 54.36 ± 8.30 | 64.29 ± 3.23 | +4.88 |
| Electric | 5 | 75.11 ± 2.67 | 72.58 ± 1.61 | 74.63 ± 2.76 | −0.48 |
| Sleep | 1 | 27.99 ± 15.92 | 13.16 ± 9.18 | 47.86 ± 13.14 | +19.87 |
| Sleep | 5 | 65.04 ± 2.66 | 58.80 ± 2.82 | 68.07 ± 5.13 | +3.03 |
| Insect | 1 | 26.17 ± 10.85 | 10.94 ± 0.64 | 29.96 ± 6.25 | +3.79 |
| Insect | 5 | 56.02 ± 1.41 | 49.60 ± 0.54 | 56.94 ± 1.39 | +0.92 |
With supervision and readout aligned, StreamDC has higher means in 19/20 comparisons: 9/10 against Random and 10/10 against K-center. At SPC1, it exceeds both on every dataset, by 0.73–19.87 points over the stronger coreset. Thus, the advantage of the complete synthesis-and-decoding framework persists beyond access to teacher supervision and temporal augmentation, most clearly at the tightest budget. The coresets' improvement also shows that our readout is useful beyond synthesized inputs. We expanded the discussion of the submitted Table 2 accordingly (Section 5.3); KL-only results and training details are in Appendix E.7 (Tables 22–23).
A.4. Cyclic windows during synthesis and decoding.
To separate the two stages as you suggested, we independently include or remove cyclic windows during synthesis and decoding on all five datasets with ShapeCond. L denotes linear-only and H hybrid readouts including cyclic completion; the first letter is synthesis and the second student decoding. SPC1 accuracy (%) is mean ± standard deviation.
| Dataset | LL | LH | HL | HH |
|---|---|---|---|---|
| HAR | 76.73 ± 4.16 | 84.89 ± 2.62 | 79.07 ± 4.06 | 86.35 ± 2.10 |
| FacesUCR | 90.52 ± 1.56 | 93.70 ± 0.62 | 90.27 ± 0.98 | 93.80 ± 0.54 |
| Electric | 55.37 ± 10.35 | 62.17 ± 8.96 | 56.58 ± 3.94 | 64.29 ± 3.23 |
| Sleep | 46.84 ± 13.38 | 46.43 ± 14.57 | 45.06 ± 12.02 | 47.86 ± 13.14 |
| Insect | 17.67 ± 7.45 | 29.50 ± 6.63 | 19.96 ± 7.66 | 29.96 ± 6.25 |
At SPC1, complete HH has the highest reported mean on all five datasets. With hybrid decoding fixed, cyclic synthesis gives comparable or better accuracy (HH−LH: 0.10–2.12 points). With hybrid synthesis fixed, cyclic decoding gives 2.80–10.00 points (HH−HL). These comparisons support learning the memory with the contexts in which it will be used and retaining those contexts during student training. SPC5 mean accuracies (%) are:
| Dataset | LL | LH | HL | HH |
|---|---|---|---|---|
| HAR | 93.79 | 94.07 | 93.91 | 93.92 |
| FacesUCR | 95.53 | 95.19 | 95.26 | 95.40 |
| Electric | 74.71 | 75.58 | 74.35 | 74.63 |
| Sleep | 67.16 | 67.55 | 67.88 | 68.07 |
| Insect | 54.75 | 56.66 | 54.96 | 56.94 |
At SPC5, the variants achieve broadly similar accuracy, with dataset-dependent differences. This complements the SPC1 result, where pure temporal origins are scarcest and complete HH has the highest mean throughout. We included both budgets in Appendix E.8 (Table 24) and connected this stage ablation to the storage–placement motivation in the main text (Section 5.4).
We hope these controls resolve the attribution concerns and strengthen the evidence for the practical value you identified.
Response to Reviewer JTN4 (1/2)
Thank you for your thoughtful assessment and support for the practical value of the framework. Your suggestions helped us sharpen its positioning and strengthen the evidence separating synthesis and student training. We address each point below.
A.1. Relationship to PoDD and the methodological contribution.
We appreciate the suggestion to make the connection to PoDD more explicit. Building on the discussion in Section 2 and Appendix C.1, we have expanded the main-text explanation of the shared foundations and the temporal problem that motivates our design.
At SPC1, a class has only one length-L segment, so a contained linear readout has just one start. Increasing linear overlap cannot expose the same class evidence at additional pure-class origins. StreamDC resolves this by combining a global linear memory with cycles confined to individual class segments: global windows expose contiguous and cross-class contexts, while cyclic completion supplies the missing same-class origins. Both families jointly optimize the same stored signal; decoding then uses an independently chosen stride to reuse that signal more densely.
Class ordering follows the existing idea of arranging compatible neighbors, instantiated here using distances between sampled time-series class means. For labeling, PoDD uses a fixed spatial layout or learned label field, whereas StreamDC assigns synthesis targets by temporal occupancy and uses the backend's teacher predictions for student training. PoDD, Section 4
The additional methodological contribution is a memory learned jointly for class-local temporal reuse and global contextual composition, with independent control over synthesis and decoding density. This changes which temporal contexts can be represented at fixed storage and how their supervision shapes the shared signal. In particular, ordinary contained-window overlap cannot supply the additional pure-class origins at SPC1. The linear-only and stage-separated controls directly test this design and its role in the complete synthesis-and-decoding framework.
A.2. Contribution of joint synthesis under the same hybrid readout.
We have extended the post-hoc control to all five datasets, three backends, and both budgets. Holding the proposed hybrid decoder fixed lets us examine the additional effect of optimizing the shared memory for its readouts. Joint synthesis gives higher means in 16/30 configurations; on HAR at SPC1, the gains are +3.37/+2.47/+5.51 for ShapeCond/SRe²L-style/G-VBSM. Applying the hybrid decoder after independent synthesis also improves over the original independent baseline in all 30 configurations and supplies the larger share of the overall gain. The differences below are StreamDC minus post-hoc in percentage points.
We retain joint synthesis plus hybrid decoding as the main method: synthesis adapts the shared signal to the contexts used for supervision, and decoding exposes the learned memory more densely. The complete procedure improves over the corresponding independent baseline in all 30 main configurations. The new discussion develops the interpretation of these complementary stages already provided by the original Table 3 (Section 5.4). The post-hoc controls retain the same hybrid readout, backend supervision, and epoch budget; implementation details are in Appendix E.1 (Tables 12–13).