Automated Graph Self-supervised Learning via Multi-teacher Knowledge Distillation

Self-supervised learning on graphs has recently achieved remarkable success in graph representation learning. With hundreds of self-supervised pretext tasks proposed over the past few years, the research community has greatly developed, and the key is no longer to design more powerful but complex pretext tasks, but to make more effective use of those already on hand. This paper studies the problem of how to automatically, adaptively, and dynamically learn instance-level self-supervised learning strategies for each node from a given pool of pretext tasks. In this paper, we propose a novel multi-teacher knowledge distillation framework for Automated Graph Self-Supervised Learning (AGSSL), which consists of two main branches: (i) Knowledge Extraction: training multiple teachers with different pretext tasks, so as to extract different levels of knowledge with different inductive biases; (ii) Knowledge Integration: integrating different levels of knowledge and distilling them into the student model. Without simply treating different teachers as equally important, we provide a provable theoretical guideline for how to integrate the knowledge of different teachers, i.e., the integrated teacher probability should be close to the true Bayesian class-probability. To approach the theoretical optimum in practice, two adaptive knowledge integration strategies are proposed to construct a relatively "good" integrated teacher. Extensive experiments on eight datasets show that AGSSL can benefit from multiple pretext tasks, outperforming the corresponding individual tasks; by combining a few simple but classical pretext tasks, the resulting performance is comparable to other leading counterparts.

Teaching Yourself:c Graph Self-Distillation on Neighborhood for Node Classification

Recent years have witnessed great success in handling graph-related tasks with Graph Neural Networks (GNNs). Despite their great academic success, Multi-Layer Perceptrons (MLPs) remain the primary workhorse for practical industrial applications. One reason for this academic-industrial gap is the neighborhood-fetching latency incurred by data dependency in GNNs, which make it hard to deploy for latency-sensitive applications that require fast inference. Conversely, without involving any feature aggregation, MLPs have no data dependency and infer much faster than GNNs, but their performance is less competitive. Motivated by these complementary strengths and weaknesses, we propose a Graph Self-Distillation on Neighborhood (GSDN) framework to reduce the gap between GNNs and MLPs. Specifically, the GSDN framework is based purely on MLPs, where structural information is only implicitly used as prior to guide knowledge self-distillation between the neighborhood and the target, substituting the explicit neighborhood information propagation as in GNNs. As a result, GSDN enjoys the benefits of graph topology-awareness in training but has no data dependency in inference. Extensive experiments have shown that the performance of vanilla MLPs can be greatly improved with self-distillation, e.g., GSDN improves over stand-alone MLPs by 15.54\% on average and outperforms the state-of-the-art GNNs on six datasets. Regarding inference speed, GSDN infers 75X-89X faster than existing GNNs and 16X-25X faster than other inference acceleration methods.

Are Gradients on Graph Structure Reliable in Gray-box Attacks?

Graph edge perturbations are dedicated to damaging the prediction of graph neural networks by modifying the graph structure. Previous gray-box attackers employ gradients from the surrogate model to locate the vulnerable edges to perturb the graph structure. However, unreliability exists in gradients on graph structures, which is rarely studied by previous works. In this paper, we discuss and analyze the errors caused by the unreliability of the structural gradients. These errors arise from rough gradient usage due to the discreteness of the graph structure and from the unreliability in the meta-gradient on the graph structure. In order to address these problems, we propose a novel attack model with methods to reduce the errors inside the structural gradients. We propose edge discrete sampling to select the edge perturbations associated with hierarchical candidate selection to ensure computational efficiency. In addition, semantic invariance and momentum gradient ensemble are proposed to address the gradient fluctuation on semantic-augmented graphs and the instability of the surrogate model. Experiments are conducted in untargeted gray-box poisoning scenarios and demonstrate the improvement in the performance of our approach.

Exploring Generative Neural Temporal Point Process

Temporal point process (TPP) is commonly used to model the asynchronous event sequence featuring occurrence timestamps and revealed by probabilistic models conditioned on historical impacts. While lots of previous works have focused on `goodness-of-fit' of TPP models by maximizing the likelihood, their predictive performance is unsatisfactory, which means the timestamps generated by models are far apart from true observations. Recently, deep generative models such as denoising diffusion and score matching models have achieved great progress in image generating tasks by demonstrating their capability of generating samples of high quality. However, there are no complete and unified works exploring and studying the potential of generative models in the context of event occurence modeling for TPP. In this work, we try to fill the gap by designing a unified \textbf{g}enerative framework for \textbf{n}eural \textbf{t}emporal \textbf{p}oint \textbf{p}rocess (\textsc{GNTPP}) model to explore their feasibility and effectiveness, and further improve models' predictive performance. Besides, in terms of measuring the historical impacts, we revise the attentive models which summarize influence from historical events with an adaptive reweighting term considering events' type relation and time intervals. Extensive experiments have been conducted to illustrate the improved predictive capability of \textsc{GNTPP} with a line of generative probabilistic decoders, and performance gain from the revised attention. To the best of our knowledge, this is the first work that adapts generative models in a complete unified framework and studies their effectiveness in the context of TPP. Our codebase including all the methods given in Section.5.1.1 is open in \url{https://github.com/BIRD-TAO/GNTPP}. We hope the code framework can facilitate future research in Neural TPPs.

CoSP: Co-supervised pretraining of pocket and ligand

Can we inject the pocket-ligand interaction knowledge into the pre-trained model and jointly learn their chemical space? Pretraining molecules and proteins has attracted considerable attention in recent years, while most of these approaches focus on learning one of the chemical spaces and lack the injection of biological knowledge. We propose a co-supervised pretraining (CoSP) framework to simultaneously learn 3D pocket and ligand representations. We use a gated geometric message passing layer to model both 3D pockets and ligands, where each node's chemical features, geometric position and orientation are considered. To learn biological meaningful embeddings, we inject the pocket-ligand interaction knowledge into the pretraining model via contrastive loss. Considering the specificity of molecules, we further propose a chemical similarity-enhanced negative sampling strategy to improve the contrastive learning performance. Through extensive experiments, we conclude that CoSP can achieve competitive results in pocket matching, molecule property predictions, and virtual screening.

SimVP: Simpler yet Better Video Prediction

From CNN, RNN, to ViT, we have witnessed remarkable advancements in video prediction, incorporating auxiliary inputs, elaborate neural architectures, and sophisticated training strategies. We admire these progresses but are confused about the necessity: is there a simple method that can perform comparably well? This paper proposes SimVP, a simple video prediction model that is completely built upon CNN and trained by MSE loss in an end-to-end fashion. Without introducing any additional tricks and complicated strategies, we can achieve state-of-the-art performance on five benchmark datasets. Through extended experiments, we demonstrate that SimVP has strong generalization and extensibility on real-world datasets. The significant reduction of training cost makes it easier to scale to complex scenarios. We believe SimVP can serve as a solid baseline to stimulate the further development of video prediction. The code is available at \href{https://github.com/gaozhangyang/SimVP-Simpler-yet-Better-Video-Prediction}{Github}.

Hyperspherical Consistency Regularization

Recent advances in contrastive learning have enlightened diverse applications across various semi-supervised fields. Jointly training supervised learning and unsupervised learning with a shared feature encoder becomes a common scheme. Though it benefits from taking advantage of both feature-dependent information from self-supervised learning and label-dependent information from supervised learning, this scheme remains suffering from bias of the classifier. In this work, we systematically explore the relationship between self-supervised learning and supervised learning, and study how self-supervised learning helps robust data-efficient deep learning. We propose hyperspherical consistency regularization (HCR), a simple yet effective plug-and-play method, to regularize the classifier using feature-dependent information and thus avoid bias from labels. Specifically, HCR first projects logits from the classifier and feature projections from the projection head on the respective hypersphere, then it enforces data points on hyperspheres to have similar structures by minimizing binary cross entropy of pairwise distances' similarity metrics. Extensive experiments on semi-supervised and weakly-supervised learning demonstrate the effectiveness of our method, by showing superior performance with HCR.

Discovering the Representation Bottleneck of Graph Neural Networks from Multi-order Interactions

Most graph neural networks (GNNs) rely on the message passing paradigm to propagate node features and build interactions. Recent works point out that different graph learning tasks require different ranges of interactions between nodes. To investigate the underlying mechanism, we explore the capacity of GNNs to capture pairwise interactions between nodes under contexts with different complexities, especially for their graph-level and node-level applications in scientific domains like biochemistry and physics. When formulating pairwise interactions, we study two standard graph construction methods in scientific domains, i.e., K-nearest neighbor (KNN) graphs and fully-connected (FC) graphs. Furthermore, we demonstrate that the inductive bias introduced by KNN-graphs and FC-graphs inhibits GNNs from learning the most informative order of interactions. Such a phenomenon is broadly shared by several GNNs for different graph learning tasks and prevents GNNs from reaching the global minimum loss, so we name it a representation bottleneck. To overcome that, we propose a novel graph rewiring approach based on the pairwise interaction strengths to adjust the reception fields of each node dynamically. Extensive experiments in molecular property prediction and dynamic system forecast prove the superiority of our method over state-of-the-art GNN baselines. Besides, this paper provides a reasonable explanation of why subgraphs play a vital role in determining graph properties. The code is available at https://github.com/smiles724/bottleneck.