Let g[1](zx) be g(zx) and W[1] be W for notation simplicity. Consider each dimension's scalar output ofg(zx), and it is denoted asg p (zx) where p is an index of the output dimension. For each AL round, a target modelΘis trained via stochastic gradient descent(SGD) using IN examples in the labeled setSL (Lines 3-5). The initial learning rate of0.1 is decayed by a factor of 0.1 at 50% and 75% of the total training iterations. Owing to the ability to find the best balance between purity and informativeness, MQ-Net achieves the highest accuracy on every AL round.

Neural Information Processing Systems http://nips.cc/

With a similar goal of sharpening representation, later Transformer-style solutions [7-9,88, 89] empower attentive networks with, for instance, local contiguity [7] and multi-level feature aggregation [9,10].

Learning (GCL) frameworks are hampered by the specificity, complexity, and incompleteness of their GA techniques.

We thank all the reviewers for their supportive and insightful comments. While kernel learning has now been1 broadly identified as important for good performance, the vast majority of approaches, while highly useful, focus2 on parametric methods that do not represent uncertainty over the values of the kernel, can be difficult to train, and3 difficult to specify inductive biases. In the camera ready, we will fix the typos and add in-text ref-33 erences to the figures we missed. Non-axis aligned methods are also possible35 with other generalizations of FFT (possibly [3]). Inthecameraready,wewillupdatethe40 figure to be on the count instead.9:

The metric backbone of a weighted graph is the union of all-pairs shortest paths.