Workshops

It is noted that representation learning normally requires a plethora of well-annotated data. Giant companies have enough money to collect well-annotated data. Nonetheless, for startups or non-profit organizations, such data is barely acquirable due to the cost of labeling data or the intrinsic scarcity in the given domain. These practical issues motivate us to research and pay attention to weakly-supervised representation learning (WSRL), since WSRL does not require such a huge amount of annotated data. We define WSRL as the collection of representation learning problem settings and algorithms that share the same goals as supervised representation learning but can only access to less supervised information than supervised representation learning. In this workshop, we discuss both theoretical and applied aspects of WSRL, which includes but not limited to the following topics:

1. Theory and applications of incomplete supervision, e.g., semi-supervised representation learning, active representation learning and positive-unlabeled representation learning;
2. Theory and applications of inexact supervision, e.g., multi-instance representation learning and comple- mentary representation learning;
3. Theory and applications of inaccurate supervision, e.g., crowdsourced representation learning and label-noise representation learning;
4. Theory and applications of cross-domain supervision, e.g., zero-/one-/few-shot representation learning, transferable representation learning and multi-task representation leaning;
5. Theory and applications of imperfect demonstration, e.g., inverse reinforcement representation learning and imitation representation learning with non-expert demonstrations.

The focus of this workshop is five types of weak supervision: incomplete supervision, inexact supervision, inaccurate supervision, cross-domain supervision and imperfect demonstration. Specifically, incomplete supervision considers a subset of training data given with ground-truth labels while the other data remain unlabeled, such as semi-supervised representation learning and positive-unlabeled representation learning. Inexact supervision considers the situation where some supervision information is given but not as exacted as desired, i.e., only coarse-grained labels are available. For example, if we are considering to classify every pixel of an image, rather than the image itself, then ImageNet becomes a benchmark with inexact supervision. Besides, multi-instance representation learning belongs to inexact supervision, where we do not exactly know which instance in the bag corresponds to the given ground-truth label. Inaccurate supervision considers the situation where the supervision information is not always the ground-truth, such as label-noise representation learning. Cross-domain supervision considers the situation where the supervision information is scarce or even non-existent in the current domain but can be possibly derived from other domains. Examples of cross-domain supervision appear in zero-/one-/few-shot representation learning, where external knowledge from other domains is usually used to overcome the problem of too few or even no supervision in the original domain. Imperfect demonstration considers the situation for inverse reinforcement representation learning and imitation representation learning, where the agent learns with imperfect or non-expert demonstrations. For example, AlphaGo learns a policy from a sequence of states and actions (expert demonstration). Even if an expert player wins a game, it is not guaranteed that every action in the sequence is optimal.

This workshop will discuss the fundamental theory of weakly-supervised representation learning. Although theories of weakly-supervised statistical learning already exist, extending these results for weakly-supervised representation learning is still a challenge. Besides, this workshop also discusses on broad applications of weakly-supervised representation learning, such as weakly-supervised object detection (computer vision), weakly-supervised sequence modeling (natural language processing), weakly-supervised cross-media retrieval (information retrieval), and weakly-supervised medical image segmentation (healthcare analysis).

According to a United Nations’ report on World Population Aging (2015), the number of people in the world aged 60 or over is projected to grow to 2.1 billion by 2050. Aging can come with various complexities and challenges, such as decline in physical, cognitive and mental health of a person. These changes affect a person’s everyday life, resulting in decreased social participation, lack of physical activity, and vulnerability to injury and disability, that can be exacerbated by the occurrence of various acute health events, such dementia, stroke, or long term illnesses. Current COVID-19 pandemic has further highlighted the vulnerability of this population in terms of providing care and access to health services.

The field of assistive technology amalgamates several multi-disciplinary areas including computer science, rehabilitation engineering, data mining, clinical studies, health care, and psychology. The idea of assistive technological solutions is to promote independent, active and healthy aging with a specific focus on older adults, and those living with mild cognitive impairments.

Collecting and mining health data using assistive technology devices is a challenging task. Leveraging Artificial Intelligence (AI) techniques and building novel machine learning (ML) models is essential to make advancements in the field of aging and technology. Building AI models on health data will facilitate independent assisted living, promote healthy and active lifestyle, and manage rehabilitation routines effectively. To reason about the collected data, to classify it and to detect abnormalities, new AI tools and methods are required.

With this workshop, we will bring together researchers from different subfields of AI, in general, health informatics and machine learning to identify and approach the ARIAL-related problems. We will also facilitate discussion, interaction, and comparison of approaches, methods, and ideas related to the domain of aging and technology.