Learning modular structures which reflect the dynamics of the environment can lead to better
generalization and robustness to changes which only affect a few of the underlying causes …

Given the input graph and its label/property, several key problems of graph learning, such as
finding interpretable subgraphs, graph denoising and graph compression, can be attributed …

For unsupervised domain adaptation problems, the strategy of aligning the two domains in
latent feature space through adversarial learning has achieved much progress in image …

Learning effective joint embedding for cross-modal data has always been a focus in the field
of multimodal machine learning. We argue that during multimodal fusion, the generated …

The ability for policies to generalize to new environments is key to the broad application of
RL agents. A promising approach to prevent an agent's policy from overfitting to a limited set …

Despite recent successes of reinforcement learning (RL), it remains a challenge for agents
to transfer learned skills to related environments. To facilitate research addressing this …

Efficient exploration under sparse rewards remains a key challenge in deep reinforcement
learning. Previous exploration methods (eg, RND) have achieved strong results in multiple …

Abstract Knowledge distillation is an effective approach to learn compact models (students)
with the supervision of large and strong models (teachers). As empirically there exists a …

Reinforcement learning encounters major challenges in multi-agent settings, such as
scalability and non-stationarity. Recently, value function factorization learning emerges as a …

Subgraph recognition aims at discovering a compressed substructure of a graph that is most
informative to the graph property. It can be formulated by optimizing Graph Information …