This is an international workshop on weakly supervised learning. The main goal of this workshop is to discuss challenging research topics in weakly supervised learning areas such as semi-supervised learning, positive-unlabeled learning, label noise learning, partial label learning, and self-supervised learning, as well as the foster collaborations among universities and institutes.

Program

Venue & Date

Workshop Venue: Creative Suite 512 of University of Queensland, Brisbane City Campus, Brisbane, Australia.

Workshop Date: November 26 09:30--17:00, November 27 09:30--16:00 and November 28 09:30--16:30 (Brisbane time (GMT+10)).

Banquet Venue: 3 Bamboo Seafood Restaurant, 6 Angel St, Eight Mile Plains QLD 4113

Date: November 27 17:45 - (Brisbane time (GMT+10)).

Schedule

The workshop will use Brisbane time (GMT+10) for scheduling, and it will be combined with invited talks and contributed talks.

Zoom: https://uqz.zoom.us/j/88582887931

***The previous talk's speaker will be the host for the next talk.***

Registration

Please complete your registration through WSL 2024 Registration Link by Nov 1st. The registration fee is AUD 375 (including 10% GST), covering the coffee breaks and the lunches for three days.

Topics

Overview

Machine learning should not be accessible only to those who can pay. Specifically, modern machine learning is migrating to the era of complex models (e.g., deep neural networks), which require a plethora of well-annotated data. Giant companies have enough money to collect well-annotated data. However, 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 learning (WSL), since WSL does not require such a huge amount of annotated data. We define WSL as the collection of machine learning problem settings and algorithms that share the same goals as supervised learning but can only access to less supervised information than supervised learning. In this workshop, we discuss both theoretical and applied aspects of WSL.

This workshop is a series of our previous workshops at ACML 2019, SDM 2020, ACML 2020, IJCAI 2021, and ACML 2021. Our particular technical emphasis at this workshop is incomplete supervision, inexact supervision, inaccurate supervision, cross-domain supervision, imperfect demonstration, and weak adversarial supervision. Meanwhile, this workshop will also focus on WSL for Science and Social Good, such as WSL for COVID-19, WSL for healthcare, WSL for climate change, WSL for remote sensing, and new public WSL datasets regarding the scientific scenarios.

Topics of Interest

WSL workshop includes (but not limited to) the following topics:

• Algorithms and theories of incomplete supervision, e.g., semi-supervised learning, active learning, and positive-unlabeled learning;
• Algorithms and theories of inexact supervision, e.g., multi-instance learning, complementary learning, and open-set learning;
• Algorithms and theories of inaccurate supervision, e.g., crowdsourced learning and label-noise learning;
• Algorithms and theories of cross-domain supervision, e.g., zero-/one-/few-shot learning, transferable learning, and multi-task learning;
• Algorithms and theories of imperfect demonstration, e.g., inverse reinforcement learning and imitation learning with non-expert demonstrations;
• Algorithms and theories of adversarial weakly-supervised learning, e.g., adversarial semi-supervised learning and adversarial label-noisy learning;
• Algorithms and theories of self-supervision, e.g., contrastive learning and autoencoder learning;
• Broad applications of weakly supervised learning in the field of computer science, such as weakly supervised object detection (computer vision), weakly supervised sequence modeling (natural language processing), and weakly supervised cross-media retrieval (information retrieval).
• WSL for science and social good, such as WSL for COVID-19, WSL for healthcare, WSL for climate change, and WSL for remote sensing, meanwhile, new public datasets regarding the above WSL research directions (new focus).

Further Descriptions

The focus of this workshop is six types of weak supervision: incomplete supervision, inexact supervision, inaccurate supervision, cross-domain supervision, imperfect demonstration, and weak adversarial supervision, which are briefly introduced below.

• Incomplete supervision considers a subset of training data given with ground-truth labels while the other data remain unlabeled, such as semi-supervised learning and positive-unlabeled 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 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 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 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 learning and imitation 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.
• Weak adversarial supervision considers the situation where weak supervision meets adversarial robustness. Since machine learning models are increasingly deployed in real-world applications, their security attracts more and more attention from both academia and industry. Therefore, many robust learning algorithms aim to prevent various evasion attacks, e.g., adversarial attacks, privacy attacks, model stealing attacks, and so on. However, almost all those robust algorithms (against evasion attacks) implicitly assume the strong supervision signals (no noisy labels in the training data), which hardly meets the requirements in practice. Therefore, when we develop evasion-robust algorithms, it is very practical/urgent to consider the supervision signals are imperfect.
• Self-supervision considers the unsupervised situation, and it pre-trains a generic feature representation by autonomously building the pseudo supervision (e.g., the similarity contrast and sample reconstruction) from the raw data, the learned representation can be applied in various downstream tasks such as classification, retrieval, and clustering.

Meanwhile, this workshop will continue discussing broad applications of weakly supervised learning in the field of computer science, such as weakly supervised object detection (computer vision), weakly supervised sequence modeling (natural language processing), and weakly supervised cross-media retrieval (information retrieval).

Organizers

General Chair

Masashi Sugiyama, RIKEN / The University of Tokyo, Japan.

Program Chair

Miao Xu, The University of Queensland, Australia.

Program Co-Chairs

Bo Han, Hong Kong Baptist University, Hong Kong SAR, China.

Tongliang Liu, The University of Sydney, Australia.

Gang Niu, RIKEN, Japan.

Accommodations

There are three hotels close to the workshop venue offering special prices for our participants. They have asked not to share the information on our website, so if you are interested, please contact the program chair (Prof. Miao Xu) directly.

Brisbane Local Information

Brisbane Weather (Nov 25 - Nov 29)

Source: Weather.com (as of November 19, 2024)

Travel Recommendations: It is summer here! We recommend wearing light, breathable clothing and applying sunscreen due to warm temperatures and extreme UV common in Brisbane. Carry an umbrella and use sun protection simultaneously, as the weather can shift from high UV to sudden showers or hailstorms. The workshop will be indoors with air conditioning, so bring a light jacket for comfort. It is best to stay in a safe place during storms. Dr. Miao Xu will monitor weather broadcasts and send email announcements in case of any (unlikely) extreme weather conditions.

Local Transportation

Brisbane offers a range of transportation options for convenient travel within the city and to/from workshop venues. Currently, QLD government offers 50 cent flat rate public transport fares which is applicable to bus, train and ferry. You may purchase a Go Card at the airport or major stations to better access these public transportations.

Travel to and from the Airport

The Brisbane Airport (BNE) is well connected to the city center with a few options.

• Airtrain: A direct rail link between the airport and Brisbane's CBD, operating every 15-30 minutes. The journey takes about 20 minutes. Airtrain services between Brisbane Airport and Brisbane City stations will be half-price, costing $10.95 currently. Book roundtrip Airtrain ahead at here.
• Taxis: Available 24/7 from designated airport pick-up areas. Travel time to the CBD is around 20-30 minutes, depending on traffic.
• Uber/Didi: Similar to Taxis, but are more flexible and often cost-effective.

Travel to and from the Banquet Venue

For travel to and from the banquet venue, consider the following options:

• Taxi and Ride-Sharing: Services such as Uber, DiDi, and local taxi companies provide reliable transport options to and from the venue. Uber/Didi usually costs $30-50 and takes 20-60 mins, depending on the traffic condition.
• Public Buses: It is better to check Google Map for the latest route and schedule information. One example could be

Brisbane and Around - Places to Visit

Brisbane offers a variety of attractions that cater to all interests, from cultural sites to natural wonders. Below, we’ve organized key places to visit based on their distance from the CBD.

Within Walking Distance from CBD

• South Bank Parklands: A vibrant area featuring lush gardens, walking paths, the man-made Streets Beach, and the Wheel of Brisbane for city views.
• Brisbane City Botanic Garden: A peaceful oasis with scenic river views, perfect for picnics and leisurely strolls.
• Queensland Art Gallery and Gallery of Modern Art (QAGOMA): A must-visit for art lovers, showcasing contemporary and historical art.
• Kangaroo Point Cliffs and Parks: Great for enjoying panoramic views of the Brisbane River and skyline, popular for walks and picnics.
• Riverside and Historical Architecture Tour: Simply walking around the workshop venue, you can take in the riverside atmosphere, admire the historical architecture, and experience Brisbane’s vivid café and brunch culture.
• Brisbane River Ferries:: A scenic and enjoyable way to travel. The CityCat service provides routes along the Brisbane River and under the Story Bridge, offering a unique view of the city and a relaxing travel experience. It costs only 50 cents:)

Within 10 Kilometers from CBD

• Lone Pine Koala Sanctuary: The world's first and largest koala sanctuary, where you can cuddle a koala and see other native Australian wildlife. (~10 km)
• Mount Coot-tha Lookout: Offers panoramic views of Brisbane and is a great spot for hiking and relaxing at the café. (~7 km)

Further than 10 Kilometers from CBD

For those looking to explore beyond the city center, Brisbane is surrounded by stunning destinations that are well worth visiting. If you plan to enjoy bush walks, be sure to protect yourself from ticks for a safe and enjoyable experience.

• Sunshine Coast City: A beautiful region known for its pristine beaches, surf spots, and relaxed atmosphere. Perfect for day trips or longer stays.
• Gold Coast City: Famous for its long sandy beaches, world-class surfing, vibrant nightlife, and theme parks like Dreamworld and Sea World.
• Mount Tamborine: A scenic spot in the Gold Coast hinterland known for its lush rainforests, stunning lookouts, and local artisan markets.
• North Stradbroke Island: A serene island escape with white sandy beaches, clear waters, and opportunities for wildlife spotting, such as dolphins and whales.
• Springbrook National Park: Part of the Gondwana Rainforests, this park offers breathtaking waterfalls, dense rainforests, and scenic hiking trails.

Previous Workshops

WSL 2023 Workshop, Tokyo, Japan.

ACML2022 WSL Workshop, Online.

ACML2021 WSL Workshop, Online.

IJCAI2021 WSRL Workshop, Online.

ACML2020 WSRL Workshop, Online.

SDM2020 WSUL Workshop, Ohio, United States.

ACML2019 WSL Workshop, Nagoya, Japan.