One starting point in this direction would be to2 consider the simplified setting of contextual bandits with linear reward functions.

We present novel graph kernels for graphs with node and edge labels that have ordered neighborhoods, i.e. when neighbor nodes followanorder.

In open-world scenarios, where both novel classes and domains may exist, an ideal segmentation model should detect anomaly classes for safety and generalize to new domains.

This sampling process is embodied as the policyπ, which is responsible for outputting an actiona conditioned on past environmental states{s}.

Reviewer #4: Thank you for thorough review and comments.

In this section, we show the proofs of the results in the main body. Eq. (1) satisfies the triangle inequality, i.e., for any scoring functions For the second inequality, we prove it similarly. Before we present the proof of the theorem, we first provide some lemmas. By applying Lemma A.2, the following holds with probability at least 1 α: null R F). Thus we have: null R A.1, we can get that the margin loss satisfies the triangle inequality. By Lemma A.4, we have R By Theorem 4.4, the following holds for any Based on Theorem A.6, the following standard error bound for gradual AST can be derived similarly to Corollary 4.6.

Empirically, the gradual self-training method greatly improves the target domain's accuracy compared

We consider a family of problems that are concerned about making predictions for the majority of unlabeled, graph-structured data samples based on a small proportion of labeled samples. Relational information among the data samples, often encoded in the graph/network structure, is shown to be helpful for these semi-supervisedlearningtasks.

We conduct a systematic comparison of methods in a variety of domains, varying thenumber oflabeled instances available inthetargetdomain (k), as well as the number of target-domain classes.