Related papers: Individual and Structural Graph Information Bottle…

We propose a novel information bottleneck (IB) method named Drop-Bottleneck, which discretely drops features that are irrelevant to the target variable. Drop-Bottleneck not only enjoys a simple and tractable compression objective but also…

Graph Neural Networks (GNNs) often encounter significant performance degradation under distribution shifts between training and test data, hindering their applicability in real-world scenarios. Recent studies have proposed various methods…

When testing data and training data come from different distributions, deep neural networks (DNNs) will face significant safety risks in practical applications. Therefore, out-of-distribution (OOD) detection techniques, which can identify…

Task-oriented communication aims to extract and transmit task-relevant information to significantly reduce the communication overhead and transmission latency. However, the unpredictable distribution shifts between training and test data,…

Deep neural networks typically learn spatially entangled representations that conflate discriminative foreground features with spurious background correlations, thereby undermining model interpretability and robustness. We propose a novel…

Although dynamic graph neural networks (DyGNNs) have demonstrated promising capabilities, most existing methods ignore out-of-distribution (OOD) shifts that commonly exist in dynamic graphs. Dynamic graph OOD generalization is non-trivial…

Systematics contaminate observables, leading to distribution shifts relative to theoretically simulated signals-posing a major challenge for using pre-trained models to label such observables. Since systematics are often poorly understood…

Graphs are a fundamental data structure for representing relational information in domains such as social networks, molecular systems, and knowledge graphs. However, graph learning models often suffer from limited generalization when…

Graph-level anomaly detection (GLAD) aims to identify graphs that exhibit notable dissimilarity compared to the majority in a collection. However, current works primarily focus on evaluating graph-level abnormality while failing to provide…

Graph Neural Networks (GNNs) suffer from over-squashing in deep message passing, where information from exponentially growing neighborhoods is compressed into fixed-dimensional representations. We show that this issue becomes a distinct…

Graph Out-of-Distribution (OOD) detection aims to identify whether a test graph deviates from the distribution of graphs observed during training, which is critical for ensuring the reliability of Graph Neural Networks (GNNs) when deployed…

Molecular dynamics simulations offer detailed insights into atomic motions but face timescale limitations. Enhanced sampling methods have addressed these challenges but even with machine learning, they often rely on pre-selected…

We tackle a common domain adaptation setting in causal systems. In this setting, the target variable is observed in the source domain but is entirely missing in the target domain. We aim to impute the target variable in the target domain…

Detecting out-of-distribution (OOD) inputs is a principal task for ensuring the safety of deploying deep-neural-network classifiers in open-set scenarios. OOD samples can be drawn from arbitrary distributions and exhibit deviations from…

Recent pre-training strategies for molecular graphs have attempted to use 2D and 3D molecular views as both inputs and self-supervised signals, primarily aligning graph-level representations. However, existing studies remain limited in…

The discrepancy between in-distribution (ID) and out-of-distribution (OOD) samples can lead to \textit{distributional vulnerability} in deep neural networks, which can subsequently lead to high-confidence predictions for OOD samples. This…

Recently, there has been a surge of interest in developing graph neural networks that utilize the invariance principle on graphs to generalize the out-of-distribution (OOD) data. Due to the limited knowledge about OOD data, existing…

Gradient-based meta-learning (GBML) algorithms are able to fast adapt to new tasks by transferring the learned meta-knowledge, while assuming that all tasks come from the same distribution (in-distribution, ID). However, in the real world,…

Decentralized learning enables serverless training of deep neural networks (DNNs) in a distributed manner on multiple nodes. This allows for the use of large datasets, as well as the ability to train with a wide variety of data sources.…

Zero-shot learning (ZSL) aims to recognize novel classes by transferring semantic knowledge from seen classes to unseen classes. Though many ZSL methods rely on a direct mapping between the visual and the semantic space, the calibration…