Related papers: Generative Causal Representation Learning for Out-…
In many problems, the measured variables (e.g., image pixels) are just mathematical functions of the latent causal variables (e.g., the underlying concepts or objects). For the purpose of making predictions in changing environments or…
Recent advances have shown that video generation models can enhance robot learning by deriving effective robot actions through inverse dynamics. However, these methods heavily depend on the quality of generated data and struggle with…
To classify in-distribution samples, deep neural networks explore strongly label-related information and discard weakly label-related information according to the information bottleneck. Out-of-distribution samples drawn from distributions…
Context-based offline meta-reinforcement learning (OMRL) methods have achieved appealing success by leveraging pre-collected offline datasets to develop task representations that guide policy learning. However, current context-based OMRL…
Visual representations underlie object recognition tasks, but they often contain both robust and non-robust features. Our main observation is that image classifiers may perform poorly on out-of-distribution samples because spurious…
Temporal knowledge graph reasoning (TKGR) is increasingly gaining attention for its ability to extrapolate new events from historical data, thereby enriching the inherently incomplete temporal knowledge graphs. Existing graph-based…
Spatiotemporal prediction over graphs (STPG) is crucial for transportation systems. In existing STPG models, an adjacency matrix is an important component that captures the relations among nodes over graphs. However, most studies calculate…
The development and evaluation of graph neural networks (GNNs) generally follow the independent and identically distributed (i.i.d.) assumption. Yet this assumption is often untenable in practice due to the uncontrollable data generation…
Detecting Out-of-Distribution (OOD) samples in real world visual applications like classification or object detection has become a necessary precondition in today's deployment of Deep Learning systems. Many techniques have been proposed, of…
Recently in the field of unsupervised representation learning, strong identifiability results for disentanglement of causally-related latent variables have been established by exploiting certain side information, such as class labels, in…
Trajectory prediction for surrounding agents is a challenging task in autonomous driving due to its inherent uncertainty and underlying multimodality. Unlike prevailing data-driven methods that primarily rely on supervised learning, in this…
Temporal Knowledge Graph (TKG) representation learning embeds entities and event types into a continuous low-dimensional vector space by integrating the temporal information, which is essential for downstream tasks, e.g., event prediction…
Object-Centric Learning (OCL) aims to discover objects in images or videos by reconstructing the input. Representative methods achieve this by reconstructing the input as its Variational Autoencoder (VAE) discrete representations, which…
Offline reinforcement learning (RL) optimizes the policy on a previously collected dataset without any interactions with the environment, yet usually suffers from the distributional shift problem. To mitigate this issue, a typical solution…
Graphical models can represent a multivariate distribution in a convenient and accessible form as a graph. Causal models can be viewed as a special class of graphical models that not only represent the distribution of the observed system…
Despite the advantages of multi-agent reinforcement learning (MARL) for wireless use case such as medium access control (MAC), their real-world deployment in Internet of Things (IoT) is hindered by their sample inefficiency. To alleviate…
Offline goal-conditioned reinforcement learning (GCRL) provides a practical framework for obtaining goal-reaching policies from fixed datasets. However, learning a reliable goal-conditioned value function in long-horizon tasks remains…
Features of the same sample generated by different pretrained models often exhibit inherently distinct feature distributions because of discrepancies in the model pretraining objectives or architectures. Learning invariant representations…
The field of self-supervised 3D representation learning has emerged as a promising solution to alleviate the challenge presented by the scarcity of extensive, well-annotated datasets. However, it continues to be hindered by the lack of…
The goal of sequential event prediction is to estimate the next event based on a sequence of historical events, with applications to sequential recommendation, user behavior analysis and clinical treatment. In practice, the next-event…