We derive an (almost) guaranteed upper bound on the error of deep neural...
This paper focuses on supervised and unsupervised online label shift, wh...
Meeting the requirements of future services with time sensitivity and
ha...
Despite the emergence of principled methods for domain adaptation under ...
Open vocabulary models (e.g. CLIP) have shown strong performance on zero...
A number of competing hypotheses have been proposed to explain why
small...
Researchers investigating example hardness have increasingly focused on ...
For most natural language processing tasks, the dominant practice is to
...
What sorts of structure might enable a learner to discover classes from
...
We introduce the problem of domain adaptation under Open Set Label Shift...
Deep supervision, or known as 'intermediate supervision' or 'auxiliary
s...
In machine learning, we traditionally evaluate the performance of a sing...
Real-world machine learning deployments are characterized by mismatches
...
Keypoint detection plays an important role in a wide range of applicatio...
Given only positive examples and unlabeled examples (from both positive ...
Time-evolving large graph has received attention due to their participat...
In a clone node attack, an attacker attempted to physically capture the
...
The rapidly expanding nature of the Internet of Things (IoT) networks is...
Blockchain technology has taken on a leading role in today's industrial
...
To assess generalization, machine learning scientists typically either (...
With populations ageing, the number of people with dementia worldwide is...
Fog computing is a promising computing paradigm for time-sensitive Inter...
Fog computing is an emerging computing paradigm which is mainly suitable...
Modern policy gradient algorithms, notably Proximal Policy Optimization
...
Label shift describes the setting where although the label distribution ...
Fog computing is an emerging computing paradigm that has come into
consi...
Stream workflow application such as online anomaly detection or online
t...
Big data processing applications are becoming more and more complex. The...
Fog computing is a promising computing paradigm in which IoT data can be...
Emerging paradigms of big data and Software-Defined Networking (SDN) in ...
This paper proposes a novel simulator IoTSim-Edge, which captures the
be...
In the recent years, the scale of graph datasets has increased to such a...
Emerging technologies that generate a huge amount of data such as the
In...
This work focuses on building language models (LMs) for code-switched te...
Emerging technologies like the Internet of Things (IoT) require latency-...
Recommender systems have become an integral part of many social networks...
Recording and analysing environmental audio recordings has become a comm...
In this work, we examine the problem of efficiently preprocessing high v...
In this work, we present a new approach to language modeling for bilingu...