Machine learning (ML) is increasingly being used in image retrieval systems for medical decision making. One application of ML is to retrieve visually similar medical images from past patients (e.g. tissue from biopsies) to reference when making a medical decision with a new patient. However, no algorithm can perfectly capture an expert's ideal notion of similarity for every case: an image that is algorithmically determined to be similar may not be medically relevant to a doctor's specific diagnostic needs. In this paper, we identified the needs of pathologists when searching for similar images retrieved using a deep learning algorithm, and developed tools that empower users to cope with the search algorithm on-the-fly, communicating what types of similarity are most important at different moments in time. In two evaluations with pathologists, we found that these tools increased the diagnostic utility of images found and increased user trust in the algorithm. The tools were preferred over a traditional interface, without a loss in diagnostic accuracy. We also observed that users adopted new strategies when using refinement tools, re-purposing them to test and understand the underlying algorithm and to disambiguate ML errors from their own errors. Taken together, these findings inform future human-ML collaborative systems for expert decision-making.

We present a design study of the TensorFlow Graph Visualizer, part of the TensorFlow machine intelligence platform. This tool helps users understand complex machine learning architectures by visualizing their underlying dataflow graphs. The tool works by applying a series of graph transformations that enable standard layout techniques to produce a legible interactive diagram. To declutter the graph, we decouple non-critical nodes from the layout. To provide an overview, we build a clustered graph using the hierarchical structure annotated in the source code. To support exploration of nested structure on demand, we perform edge bundling to enable stable and responsive cluster expansion. Finally, we detect and highlight repeated structures to emphasize a model's modular composition. To demonstrate the utility of the visualizer, we describe example usage scenarios and report user feedback. Overall, users find the visualizer useful for understanding, debugging, and sharing the structures of their models.

Video transmission in multiparty video conferencing is challenging due to the demanding bandwidth usage and stringent latency requirement. In this paper, we systematically analyze the problem of collaborative stream routing using one-hop forwarding assistance in a bandwidth constraint environment. We model the problem as a multi-source degree-constrained multicast tree construction problem, and investigate heuristic algorithms to construct bandwidth-feasible shared multicast trees. The contribution of this work is primarily two-fold: (1) we study the solution space of finding a feasible bandwidth configuration for stream routing in a peer-to-peer (P2P) setting, and propose two heuristic algorithms that can quickly produce a bandwidth-feasible solution, making them suitable for large-scale conference sessions, (2) we conduct an empirical study using a realistic dataset and show the effectiveness of our heuristic algorithms. Various QoS metrics are taken into account to evaluate the performance of our algorithms. Finally, we discuss open issues for further exploration. The feasibility study presented in this paper will shed light on the design and implementation of practical P2P multiparty video conferencing applications.

Motivated by the problem of limited bandwidth in peer-to-peer (P2P) multi-party video conferencing systems, in this paper we propose a non-intrusive adaptive multi-media routing algorithm that effectively calculates stream routing to achieve a maximum number of receiving streams. The technique is non-intrusive in that it makes use of current streaming status to infer link bottlenecks rather than sending active probing packets, which would seriously interfere with the latency-sensitive video conferencing application and waste bandwidth. When link bottlenecks are detected, the method will adaptively calculate streaming routes, allowing bandwidth abundant peers to act as relays. To test the performance, we use real data from a world wide bandwidth distribution archive and investigate the algorithm convergence rate and distribution fairness through simulation. Results show that the technique works well to achieve effective multi-media routing for latency-sensitive video conferencing applications.