Sorry, you need to enable JavaScript to visit this website.

In this paper, we consider the problem of Federated Learning (FL) under non-i.i.d data setting. We provide an improved estimate of the empirical loss at each node by using a weighted average of losses across nodes with a penalty term. These uneven weights to different nodes are assigned by taking a novel Bayesian approach to the problem where the problem of learning for each device/node is cast as maximizing the likelihood of a joint distribution. This joint distribution is for losses of nodes obtained by using data across devices for a given neural network of a node.

There are two critical observations in multi-domain dialogue state tracking (DST) ignored in most existing work. First, the number of triples (domain-slot-value) in dialogue states generally increases with the growth of dialogue turns. Second, although dialogue states are accumulating, the difference between two adjacent turns is steadily minor. To model the two observations, we propose to divide the task into two successive procedures: progressive domain-slot tracking and shrunk value prediction.

During the COVID-19 pandemic the health authorities at airports and train stations try to screen and identify the travellers possibly exposed to the virus. However, many individuals avoid getting tested and hence may misreport their travel history. This is a challenge for the health authorities who wish to ascertain the truly susceptible cases in spite of this strategic misreporting. We investigate the problem of questioning travellers to classify them for further testing when the travellers are strategic or are unwilling to reveal their travel histories.

Ensuring performance robustness for a variety of situations that can occur in real-world environments is one of the challenging tasks in sound event classification. One of the unpredictable and detrimental factors in performance, especially in indoor environments, is reverberation. To alleviate this problem, we propose a conditioning method that provides room impulse response (RIR) information to help the network become less sensitive to environmental information and focus on classifying the desired sound.

During the COVID-19 pandemic the health authorities at airports and train stations try to screen and identify the travellers possibly exposed to the virus. However, many individuals avoid getting tested and hence may misreport their travel history. This is a challenge for the health authorities who wish to ascertain the truly susceptible cases in spite of this strategic misreporting. We investigate the problem of questioning travellers to classify them for further testing when the travellers are strategic or are unwilling to reveal their travel histories.

Some recent work treats age estimation as an ordinal ranking task and decomposes it into multiple binary classifications. However, a theoretical defect lies in this type of methods: the ignorance of possible contradictions in individual ranking results. In this paper, we partially embrace the decomposition idea and propose the Deep and Ordinal Ensemble Learning with Two Groups Classification (DOEL 2groups ) for age prediction. An important advantage of our approach is that it theoretically allows the prediction even when the contradictory cases occur.