Computer-Using Agents (CUA) enable users to automate increasingly-complex tasks using graphical interfaces such as browsers. As many potential tasks require personal data, we propose Computer-Using Personal Agents (CUPAs) that have access to an external repository of the user's personal data. Compared with CUAs, CUPAs offer users better control of their personal data, the potential to automate more tasks involving personal data, better interoperability with external sources of data, and better capabilities to coordinate with other CUPAs in order to solve collaborative tasks involving the personal data of multiple users.

I'd like to say that I was highly organized, that I knew where every box ended up and what was in each box. Most people who move know the feeling of living in boxes even after the movers have left, the days spent dodging labyrinths of teetering cardboard, their arms and legs scored with paper cuts where they misjudged that one particular stack that seemed to have taken on a malicious life of its own. In retrospect, I've decided I'm going to go truly high-tech next time: buy a batch of beacons, one for each box, my laptop open as I carefully pack each cardboard container with my sundry possessions, adding each item into a personal knowledge graph so that I can tell exactly where everything in my new house, organized by topic, by room, by owner. I will gleefully take screenshots showing how masterful my graph-fu skills are for future articles, and maybe, just maybe, I wouldn't then have to sleep on the couch at night because I inadvertently packed the family cat. Ah, who am I kidding?

I help lead a working group focused on personal knowledge graphs (PKGs). Lately, it's functioned as a discussion and demo evaluation group for new technologies and how they might be used in a knowledge graph context. Different individuals want to annotate different kinds of data. Some do a lot of research. For them, the need is to annotate the links and associated text (in a simple and ideally machine assisted way from research sources so that machines can help retrieve the right links later on and discover (or rediscover) related links.

Knowledge-driven systems for decision-making in health care applications are powerful tools to help provide actionable and explainable insights to patients and practitioners. In such systems, knowledge about the particular patient - current condition, historical ailments, etc. - is central to enable personalized health care. An example of such a system for personalized health care is a diet and lifestyle decision-making tool for diabetic patients. This system may utilize knowledge from several domain-specific knowledge graphs (KGs), such as a KG of diabetes health care guidelines from the American Diabetes Association and a KG of food and nutrition such as FoodKG [4]. Knowledge about a particular patient is used here to perform context-aware reasoning and personalization of down-stream applications. For example, what the system recommends as a "healthy" meal may differ for among patients based on personal aspects like their current weight or exercise habits. To facilitate reasoning and decision-making based on personal context, such systems can benefit from integrating personal knowledge about the patient. This extended abstract presents a brief review of existing work surrounding the concept of personal knowledge graphs (PKG), how they could be integrated into personalized healthcare as personal health knowledge graphs (PHKG), and the key gaps in existing literature that must be addressed to realize their full potential.

A personal knowledge graph comprising people as nodes, their personal data as node attributes, and their relationships as edges has a number of applications in de-identification, master data management, and fraud prevention. While artificial neural networks have led to significant improvements in different tasks in cold start knowledge graph population, the overall F1 of the system remains quite low. This problem is more acute in personal knowledge graph population which presents additional challenges with regard to data protection, fairness and privacy. In this work, we present a system that uses rule based annotators to augment training data for neural models, and for slot filling to increase the diversity of the populated knowledge graph. We also propose a representative set sampling method to use the populated knowledge graph data for downstream applications. We introduce new resources and discuss our results.

When we created Snips a few years ago, we did so because we believed in using Artificial Intelligence to solve everyday problems. From predicting passenger flow in public transport to anticipating car accidents, we always tried to find a way to bring the power of machine learning to consumers. But then, we started thinking more long term, about what will happen with all of those connected devices, bots and apps coming onto the market. What we realized is that there is no way we will be able to cope with so much technology, at least not with the current way we interact with it. After all, with only 2 devices per person on average today (a phone and a computer), we are already overwhelmed by technology. Who hasn't felt the urge to check their phone when receiving a notification, or felt desperate looking at their email inbox growing faster than they can handle?