Active Adversarial Domain Adaptation (AADA)
We propose an active learning approach for transferring representations across domains. Our approach, active adversarial domain adaptation (AADA), explores a duality between two related problems: adversarial domain alignment and importance sampling for adapting models across domains. The former uses a domain discriminative model to align domains, while the latter utilizes it to weigh samples to account for distribution shifts. Specifically, our importance weight promotes samples with large uncertainty in classification and diversity from labeled examples, thus serves as a sample selection scheme for active learning. We show that these two views can be unified in one framework for domain adaptation and transfer learning when the source domain has many labeled examples while the target domain does not. AADA provides significant improvements over fine-tuning based approaches and other sampling methods when the two domains are closely related. Results on challenging domain adaptation tasks, e.g., object detection, demonstrate that the advantage over baseline approaches is retained even after hundreds of examples being actively annotated. …

Shapley-Taylor Interaction Index
We study interactions among players in cooperative games. We propose a new interaction index called Shapley-Taylor interaction index. It decomposes the value of the game into terms that model the interactions between subsets of players, analogous to how the Taylor series represents a function in terms of its derivatives of various orders. We axiomatize the method using the standard Shapley axioms–linearity, dummy, symmetry and efficiency–and also an additional axiom that we call the interaction distribution axiom. This new axiom explicitly characterizes how inter-actions are distributed for a class of games called interaction games. We contrast the Shapley-Taylor interaction index against the previously pro-posed Shapley Interaction index and the Banzhaf interaction index (cf. [2]). …

TransferTransfo
We introduce a new approach to generative data-driven dialogue systems (e.g. chatbots) called TransferTransfo which is a combination of a Transfer learning based training scheme and a high-capacity Transformer model. Fine-tuning is performed by using a multi-task objective which combines several unsupervised prediction tasks. The resulting fine-tuned model shows strong improvements over the current state-of-the-art end-to-end conversational models like memory augmented seq2seq and information-retrieval models. On the privately held PERSONA-CHAT dataset of the Conversational Intelligence Challenge 2, this approach obtains a new state-of-the-art, with respective perplexity, Hits@1 and F1 metrics of 16.28 (45 % absolute improvement), 80.7 (46 % absolute improvement) and 19.5 (20 % absolute improvement). …

Stateful DataFlow multiGraph (SDFG)
With the ubiquity of accelerators, such as FPGAs and GPUs, the complexity of high-performance programming is increasing beyond the skill-set of the average scientist in domains outside of computer science. It is thus imperative to decouple programming paradigms and architecture-specific implementation from the underlying scientific computations. We present the Stateful DataFlow multiGraph (SDFG), a data-centric intermediate representation that facilitates high performance application development and optimization. By combining fine-grained data dependencies with high-level control flow, SDFGs are both expressive and amenable to high-level program transformations, such as tiling, vectorization, and double buffering. These transformations are then applied to the SDFG in an interactive process, using extensible pattern matching and graph rewriting. To facilitate this process, we provide a graphical user interface that enables applying transformations, as well as creating custom optimizations, reusable across applications. We demonstrate SDFGs on CPUs, GPUs, and FPGAs, using a wide variety of applications and motifs — from fundamental computational kernels, through polyhedral applications, to graph analytics. We show that the representation is both expressive and performant, allowing domain scientists to develop applications that can be tuned to approach peak hardware performance without modifying the original scientific code. …