Whereas for the node injection attack, though being more practical, current approaches require training surrogate models to simulate a white-box setting, which results in significant performance downgrade when the surrogate architecture diverges from the actual victim model.
Specifically, The pre-training phase aims to comprehensively estimate the underlying graph structure by a multi-view contrastive learning framework with both intra- and inter-view link prediction tasks.
In light of this, we propose a novel knowledge Graph enhanced passage reader, namely Grape, to improve the reader performance for open-domain QA.
Self-supervised learning (SSL) for graph neural networks (GNNs) has attracted increasing attention from the graph machine learning community in recent years, owing to its capability to learn performant node embeddings without costly label information.
no code implementations • 1 Oct 2022 • Shiyu Wang, Xiaojie Guo, Xuanyang Lin, Bo Pan, Yuanqi Du, Yinkai Wang, Yanfang Ye, Ashley Ann Petersen, Austin Leitgeb, Saleh AlKhalifa, Kevin Minbiole, William Wuest, Amarda Shehu, Liang Zhao
Developing deep generative models has been an emerging field due to the ability to model and generate complex data for various purposes, such as image synthesis and molecular design.
The effectiveness is further guaranteed and proved by the gradients' distance between the subset and the full set; (ii) empirically, we discover that during the learning process of a GNN, some samples in the training dataset are informative for providing gradients to update model parameters.
Later, the trained encoder is frozen as a teacher model to distill a student model with a contrastive loss.
In light of this, we introduce the Graph Contrastive Learning with Cross-View Reconstruction (GraphCV), which follows the information bottleneck principle to learn minimal yet sufficient representation from graph data.
In light of this, few-shot learning on graphs (FSLG), which combines the strengths of graph representation learning and few-shot learning together, has been proposed to tackle the performance degradation in face of limited annotated data challenge.
Spatiotemporal graph represents a crucial data structure where the nodes and edges are embedded in a geometric space and can evolve dynamically over time.
Graph Neural Networks (GNNs) have drawn significant attentions over the years and been broadly applied to vital fields that require high security standard such as product recommendation and traffic forecasting.
To solve this problem, in this paper, we propose a novel framework - i. e., namely Adaptive Kernel Graph Neural Network (AKGNN) - which learns to adapt to the optimal graph kernel in a unified manner at the first attempt.
In this paper, we propose a holistic framework named MetaHG to automatically detect illicit drug traffickers on social media (i. e., Instagram), by tackling the following two new challenges: (1) different from existing works which merely focus on analyzing post content, MetaHG is capable of jointly modeling multi-modal content and relational structured information on social media for illicit drug trafficker detection; (2) in addition, through the proposed meta-learning technique, MetaHG addresses the issue of requiring sufficient data for model training.
To retain the heterogeneity, intra-relation aggregation is first performed over each slice of HTG to attentively aggregate information of neighbors with the same type of relation, and then intra-relation aggregation is exploited to gather information over different types of relations; to handle temporal dependencies, across-time aggregation is conducted to exchange information across different graph slices over the HTG.
Existing graph transformer models typically adopt fully-connected attention mechanism on the whole input graph and thus suffer from severe scalability issues and are intractable to train in data insufficient cases.
While many recent efforts show the effectiveness of neural network-based social recommender systems, several important challenges have not been well addressed yet: (i) The majority of models only consider users' social connections, while ignoring the inter-dependent knowledge across items; (ii) Most of existing solutions are designed for singular type of user-item interactions, making them infeasible to capture the interaction heterogeneity; (iii) The dynamic nature of user-item interactions has been less explored in many social-aware recommendation techniques.
Accordingly, accurate detection of illicit drug trafficking events (IDTEs) from social media has become even more challenging.
Unlike existing methods that focus on posting-based detection, we propose to tackle the problem of illicit drug dealer identification by constructing a large-scale multimodal dataset named Identifying Drug Dealers on Instagram (IDDIG).
To capture malware evolution, we further consider the temporal dependence and introduce a heterogeneous temporal graph to jointly model malware propagation and evolution by considering heterogeneous spatial dependencies with temporal dimensions.
We train CoTexT on different combinations of available PL corpus including both "bimodal" and "unimodal" data.
Heterogeneous graphs (HGs) also known as heterogeneous information networks have become ubiquitous in real-world scenarios; therefore, HG embedding, which aims to learn representations in a lower-dimension space while preserving the heterogeneous structures and semantics for downstream tasks (e. g., node/graph classification, node clustering, link prediction), has drawn considerable attentions in recent years.
Disentangled representation learning has recently attracted a significant amount of attention, particularly in the field of image representation learning.
In this paper, we survey and systematize the field of Adversarial Malware Detection (AMD) through the lens of a unified conceptual framework of assumptions, attacks, defenses, and security properties.
By conducting experiments with the Drebin Android malware dataset, we show that the framework can achieve a 98. 49\% accuracy (on average) against grey-box attacks, where the attacker knows some information about the defense and the defender knows some information about the attack, and an 89. 14% accuracy (on average) against the more capable white-box attacks, where the attacker knows everything about the defense and the defender knows some information about the attack.
Graph neural network (GNN) has shown superior performance in dealing with graphs, which has attracted considerable research attention recently.
The micro-dynamics describe the formation process of network structures in a detailed manner, while the macro-dynamics refer to the evolution pattern of the network scale.
With the learned importance from both node-level and semantic-level attention, the importance of node and meta-path can be fully considered.
Ranked #1 on Heterogeneous Node Classification on DBLP (PACT) 14k
Social and Information Networks
However, machine learning is known to be vulnerable to adversarial evasion attacks that manipulate a small number of features to make classifiers wrongly recognize a malware sample as a benign one.
Cryptography and Security 68-06
In this paper, we first extract the runtime Application Programming Interface (API) call sequences from Android apps, and then analyze higher-level semantic relations within the ecosystem to comprehensively characterize the apps.