This was the second meeting of the GroupSight workshop to be held at the AAAI Conference on Human Computation and Crowdsourcing (HCOMP). It was also the first time the workshop and conference were colocated with the ACM Conference on User Interface Software and Technology. The workshop was held in Quebec City, Quebec, Canada, on October 24, 2017. The workshop featured two keynote speakers in humancomputer interaction (HCI) doing research on crowdsourced image analysis. The Workshop Was Held in Quebec City, Quebec, Canada.

Designing systems and services with AI functionality as part of a care experience presents a range of challenges and opportunities. Limitations with sparse or missing data can make algorithmic training difficult, while the opaqueness of some black box methods muddies the process of interpreting outcomes. Human expertise and knowledge need to be carefully integrated at appropriate stages to inform both the AI approach and the fulfillment of the overall care cycle. Tackling this complex problem space requires a multidimensional and multi-stage approach integrating technical, social, medical, design and HCI knowledge. Based on our work creating therapeutic AI systems for cognitive and physical training, we propose six key system design challenges for consideration.

Using a graphical discrete dynamical system to model a networked social system, the problem of inferring the behavior of the system can be formulated as the problem of learning the local functions of the dynamical system. We investigate the problem assuming an active form of interaction with the system through queries. We consider two classes of local functions (namely, symmetric and threshold functions) and two interaction modes, namely batch mode (where all the queries must be submitted together) and adaptive mode (where the set of queries submitted at a stage may rely on the answers received to previous queries). We develop complexity results and efficient heuristics that produce query sets under both query modes. We demonstrate the performance of our heuristics through experiments on over 20 well-known networks.

A single image captures the appearance and position of multiple entities in a scene as well as their complex interactions. As a consequence, natural language grounded in visual contexts tends to be diverse---with utterances differing as focus shifts to specific objects, interactions, or levels of detail. Recently, neural sequence models such as RNNs and LSTMs have been employed to produce visually-grounded language. Beam Search, the standard work-horse for decoding sequences from these models, is an approximate inference algorithm that decodes the top-B sequences in a greedy left-to-right fashion. In practice, the resulting sequences are often minor rewordings of a common utterance, failing to capture the multimodal nature of source images. To address this shortcoming, we propose Diverse Beam Search (DBS), a diversity promoting alternative to BS for approximate inference. DBS produces sequences that are significantly different from each other by incorporating diversity constraints within groups of candidate sequences during decoding; moreover, it achieves this with minimal computational or memory overhead. We demonstrate that our method improves both diversity and quality of decoded sequences over existing techniques on two visually-grounded language generation tasks---image captioning and visual question generation---particularly on complex scenes containing diverse visual content. We also show similar improvements at language-only machine translation tasks, highlighting the generality of our approach.

Scan statistics is one of the most popular approaches for anomaly detection in spatial and network data. In practice, there are numerous sources of uncertainty in the observed data. However, most prior works have overlooked such uncertainty, which can affect the accuracy and inferences of such methods. In this paper, we develop the first systematic approach to incorporating uncertainty in scan statistics. We study two formulations for robust scan statistics, one based on the sample average approximation and the other using a max-min objective. We show that uncertainty significantly increases the computational complexity of these problems. Rigorous algorithms and efficient heuristics for both formulations are developed with justification of theoretical bounds. We evaluate our proposed methods on synthetic and real datasets, and we observe that our methods give significant improvement in the detection power as well as optimization objective, relative to a baseline.

Segmenting temporal data sequences is an important problem which helps in understanding data dynamics in multiple applications such as epidemic surveillance, motion capture sequences, etc. In this paper, we give DASSA, the first self-guided and efficient algorithm to automatically find a segmentation that best detects the change of pattern in data sequences. To avoid introducing tuning parameters, we design DASSA to be a multi-level method which examines segments at each level of granularity via a compact data structure called the segment-graph. We build this data structure by carefully leveraging the information bottleneck method with the MDL principle to effectively represent each segment.Next, DASSA efficiently finds the optimal segmentation via a novel average-longest-path optimization on the segment-graph. Finally we show how the outputs from DASSA can be naturally interpreted to reveal meaningful patterns. We ran DASSA on multiple real datasets of varying sizes and it is very effective in finding the time-cut points of the segmentations (in some cases recovering the cut points perfectly) as well as in finding the corresponding changing patterns.

Given a sequence of snapshots of flu propagating over a population network, can we find a segmentation when the patterns of the disease spread change, possibly due to interventions? In this paper, we study the problem of segmenting graph sequences with labeled nodes. Memes on the Twitter network, diseases over a contact network, movie-cascades over a social network, etc. are all graph sequences with labeled nodes. Most related work is on plain graphs (and hence ignore the label dynamics) or fix parameters or require much feature engineering. Instead, we propose SnapNETS, to automatically find segmentations of such graph sequences, with different characteristics of nodes of each label in adjacent segments. It satisfies all the desired properties (being parameter-free, comprehensive and scalable) by leveraging a principled, multi-level, flexible framework which maps the problem to a path optimization problem over a weighted DAG. Extensive experiments on several diverse real datasets show that it finds cut points matching ground-truth or meaningful external signals outperforming non-trivial baselines. We also show that SnapNETS scales near-linearly with the size of the input.

Learning about a new area of knowledge is challenging for novices partly because they are not yet aware of which topics are most important. The Internet contains a wealth of information for learning the underlying structure of a domain, but relevant sources often have diverse structures and emphases, making it hard to discern what is widely considered essential knowledge vs. what is idiosyncratic. Crowdsourcing offers a potential solution because humans are skilled at evaluating high-level structure, but most crowd micro-tasks provide limited context and time. To address these challenges, we present Crowdlines, a system that uses crowdsourcing to help people synthesize diverse online information. Crowdworkers make connections across sources to produce a rich outline that surfaces diverse perspectives within important topics. We evaluate Crowdlines with two experiments. The first experiment shows that a high context, low structure interface helps crowdworkers perform faster, higher quality synthesis, while the second experiment shows that a tournament-style (parallelized) crowd workflow produces faster, higher quality, more diverse outlines than a linear (serial/iterative) workflow.  

High profile large scale public events are attractive targets for terrorist attacks. The recent Boston Marathon bombings on April 15, 2013 have further emphasized the importance of protecting public events. The security challenge is exacerbated by the dynamic nature of such events: e.g., the impact of an attack at different locations changes over time as the Boston marathon participants and spectators move along the race track. In addition, the defender can relocate security resources among potential attack targets at any time and the attacker may act at any time during the event. This paper focuses on developing efficient patrolling algorithms for such dynamic domains with continuous strategy spaces for both the defender and the attacker. We aim at computing optimal pure defender strategies, since an attacker does not have an opportunity to learn and respond to mixed strategies due to the relative infrequency of such events. We propose SCOUT-A, which makes assumptions on relocation cost, exploits payoff representation and computes optimal solutions efficiently. We also propose SCOUT-C to compute the exact optimal defender strategy for general cases despite the continuous strategy spaces. SCOUT-C computes the optimal defender strategy by constructing an equivalent game with discrete defender strategy space, then solving the constructed game. Experimental results show that both SCOUT-A and SCOUT-C significantly outperform other existing strategies.

The spread of epidemics and malware is commonly modeled by diffusion processes on networks. Protective interventions such as vaccinations or installing anti-virus software are used to contain their spread. Typically, each node in the network has to decide its own strategy of securing itself, and its benefit depends on which other nodes are secure, making this a natural game-theoretic setting. There has been a lot of work on network security game models, but most of the focus has been either on simplified epidemic models or homogeneous network structure. We develop a new formulation for an epidemic containment game, which relies on the characterization of the SIS model in terms of the spectral radius of the network. We show in this model that pure Nash equilibria (NE) always exist, and can be found by a best response strategy. We analyze the complexity of finding NE, and derive rigorous bounds on their costs and the Price of Anarchy or PoA (the ratio of the cost of the worst NE to the optimum social cost) in general graphs as well as in random graph models. In particular, for arbitrary power-law graphs with exponent $\beta>2$, we show that the PoA is bounded by $O(T^{2(\beta-1)})$, where $T=\gamma/\alpha$ is the ratio of the recovery rate to the transmission rate in the SIS model. We prove that this bound is tight up to a constant factor for the Chung-Lu random power-law graph model. We study the characteristics of Nash equilibria empirically in different real communication and infrastructure networks, and find that our analytical results can help explain some of the empirical observations.