- Rating
- 3
- Confidence
- 2
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes a low-rank degree-2 convolutional unit that uses pairwise interactions to improve binarized CNNs without increasing activation precision. The authors provide theoretical results on expressive power and exact integer compilation for one-bit inputs. Experiments on 5 datasets show accuracy gains of 1.46~2.11 under matched parameter budgets, with lower activation storage and faster convergence. The paper also compares this approach with increasing activation precision and examines their hardware cost trade-offs.
Critical strengths
- The rank characterization and exact compilation results provide a solid theoretical foundation for the proposed method. The authors also clarify how pairwise interactions can improve expressiveness without increasing activation precision.
- The paper compares models under similar parameter and estimated logic budgets across 5 datasets, supported by several ablations. The proposed method achieves consistent accuracy gains of 1.46~2.11 while using roughly 1/3 of the baseline's activation storage. The analysis of faster and more stable training also provides useful insights.
Critical weaknesses
- Hardware costs are based on analytical estimates rather than actual FPGA synthesis. The experiments also do not evaluate settings where activation memory is a limiting factor. Therefore, the practical benefits in terms of hardware resources, latency, and energy efficiency remain uncertain.
- On CIFAR-10, the reported 2.11 improvement decreases to 0.38 after learning rate tuning, with overlapping seed results. Although longer training at the shared learning rate still shows a 1.5 improvement, it remains unclear whether the advantage persists when both methods are fully trained and independently tuned.
Questions for authors
- Can the authors provide FPGA synthesis results to validate the estimated hardware costs, particularly logic and memory usage, multiplier utilization, and latency?
- Does the accuracy improvement remain when both methods are trained to convergence with independently optimized learning rates?
We thank the reviewer for the positive assessment and the constructive feedback, and for acknowledging the strengths: "a solid theoretical foundation" (Strength 1), and "consistent accuracy gains" at "roughly 1/3 of the baseline's activation storage", with "useful insights" on training (Strength 2). The reviewer's summary raises no concern beyond W1 and W2. Synthesis of two layers is done (see [W1, Q1]). Compared at each model's best learning rate within Table 8's grid, the lead falls to 0.38 pp (see [W2, Q2]). In the revised PDF, revised and added text is shown in color.
[W1, Q1] Do the estimated hardware costs hold up in synthesis? Yes for the adder-tree logic, which synthesis reproduces. The multiplier costs more than the cost model assumed, which raises total logic to at least 1.175× the baseline's against the predicted 1.028×, and placement adds a cost in clock and latency. The adder tree is 2.82× and 0.99× the baseline's logic at the two synthesized layers, against the predicted 3.00× and 1.00×. The multiplier's synthesized price is in revised App. F and the reply to 4Uaf [cost model]. Memory needs no synthesis check: it counts the activation bits stored between layers, which the synthesized logic tiles do not contain, so Table 1's count stands. In memory, the pair unit (the degree-2 unit) stores 26 KiB of activations per image against the baseline's 78 (Table 1). In multipliers, it needs 2,560 across the network, and they are intrinsic at these fan-ins: building the products from AND gates would cost 86 times the factored form's logic (new, revised App. F). In clock and latency, placed and routed on a Xilinx Artix-7 (xc7a200t, speed grade -2), seed 0, the pair unit runs at 0.42 and 0.56 of the baseline's clock unpipelined. Pipelining adds registers that split the circuit into stages: the clock is set by the slowest stage, and each output takes several cycles while a new input still enters every cycle. Pipelined, with a register after every popcount and, in the pair unit, after every product as well, it runs at 0.77 and 0.95 of the baseline's clock. At layer 1 its throughput is therefore 95 percent of the baseline's, while an output takes 1.95 and 1.58 times as long (new, revised App. F; table in the reply to q1fS [W2, Q2]).
The pair unit trades added logic and multipliers for smaller activation memory, and where that exchange pays off is not yet measured. No run reaches the regime where memory binds. For the baseline it begins near 229 px inputs, where its largest activation map reaches the size of the weight memory (computed from Table 1's widths). At 64×64, the nearest measured point, the pair unit leads at the shared learning rate (reply to q1fS [W2, W3, Q4]). Energy is not measured. Revised App. F carries the synthesis and place-and-route results and the multiplier's synthesized price; see also the reply to 4Uaf [cost model].
[W2, Q2] Does the improvement remain when both are converged and independently tuned? Within Table 8's grid, the paper's tuning study, the pair unit leads at every rate, at 4e-3 by 0.17 pp, inside seed noise (Table 8). Converged at the shared rate, it leads by 1.50 pp (App. G). We have now also run the pair unit at 5e-4, the one rate the submitted Table 8 left blank for it: it reaches 86.76 ± 0.24 over three seeds (new, revised App. G). Every other cell of Table R1 is from Table 8.
Table R1. CIFAR-10 test accuracy (%), mean of three seeds, at each learning rate (Table 8, revised App. G).
What tuning shows is that the pair unit needs less tuning, not that it reaches a higher ceiling. Compared at each model's best rate, 87.05 against 86.67, the lead is 0.38 pp, inside seed noise. The pair unit at its weakest rate, 86.76, is level with the baseline at its best, and across the four rates the baseline's accuracy spans 2.93 pp, the pair unit's 0.29 (table above). The baseline's best accuracy has to be found by searching the learning rate; the pair unit's does not. Even at its best rate the baseline still gains 4.28 pp over its last 60 epochs, more than App. G's convergence criterion allows, so the 0.38 pp is an upper bound. App. G states that "the paper claims no accuracy gap over a tuned baseline".
What tuning does not change is memory: the baseline still stores three times the activations. For a degree-1 control at equal stored bits, see our reply to q1fS [W2, Q3]. Revised App. G carries the per-rate convergence numbers; see also the replies to 4Uaf [Q2] and q1fS [W1, Q1].