Classic machine learning methods are built on the $i. i. d.$ assumption that training and testing data are independent and identically distributed.
Domain generalization (DG) aims to help models trained on a set of source domains generalize better on unseen target domains.
It aims at suggesting the next POI to a user in spatial and temporal context, which is a practical yet challenging task in various applications.
In this paper, we propose a novel Stable Adversarial Learning (SAL) algorithm that leverages heterogeneous data sources to construct a more practical uncertainty set and conduct differentiated robustness optimization, where covariates are differentiated according to the stability of their correlations with the target.
We investigate the theoretical connections between graph signal processing and graph embedding models and formulate the graph embedding model as a general graph signal process with a corresponding graph filter.
In this paper, we propose Heterogeneous Risk Minimization (HRM) framework to achieve joint learning of latent heterogeneity among the data and invariant relationship, which leads to stable prediction despite distributional shifts.
Approaches based on deep neural networks have achieved striking performance when testing data and training data share similar distribution, but can significantly fail otherwise.
As a part of the value function, free from the sparse and high-variance reward signals, a high-capacity reward-independent world model is trained to simulate complex environmental dynamics under a certain goal.
It is critical yet challenging for deep learning models to properly characterize uncertainty that is pervasive in real-world environments.
In this paper, we propose a novel Heterogeneous graph neural network framework for diversified recommendation (GraphDR) in matching to improve both recommendation accuracy and diversity.
Graph Neural Networks (GNNs) have received considerable attention on graph-structured data learning for a wide variety of tasks.
We propose to address this problem by removing the dependencies between features via reweighting training samples, which results in a more balanced distribution and helps deep models get rid of spurious correlations and, in turn, concentrate more on the true connection between features and labels.
Estimating counterfactual outcome of different treatments from observational data is an important problem to assist decision making in a variety of fields.
The original design of Graph Convolution Network (GCN) couples feature transformation and neighborhood aggregation for node representation learning.
We then employ a novel gated graph attention network to encode the constructed graph for sentence matching.
Specifically, we augment the existing GNNs with stochastic node representations learned to preserve node proximities.
In this paper, we propose a novel setting of transferable black-box attack: attackers may use external information from a pre-trained model with available network parameters, however, different from previous studies, no additional training data is permitted to further change or tune the pre-trained model.
There exist two challenges: i) reconstructing a future sequence containing many behaviors is exponentially harder than reconstructing a single next behavior, which can lead to difficulty in convergence, and ii) the sequence of all future behaviors can involve many intentions, not all of which may be predictable from the sequence of earlier behaviors.
We tackle the challenge and propose an adaptive multi-channel graph convolutional networks for semi-supervised classification (AM-GCN).
In practice, there frequently exist a certain set of variables we term as fair variables, which are pre-decision covariates such as users' choices.
By assuming the relationships between causal variables and response variable are invariant across data, to address this problem, we propose a conditional independence test based algorithm to separate those causal variables with a seed variable as priori, and adopt them for stable prediction.
Machine learning algorithms with empirical risk minimization are vulnerable under distributional shifts due to the greedy adoption of all the correlations found in training data.
In particular, we develop a novel graph embedding algorithm, High-Order Proximity preserved Embedding (HOPE for short), which is scalable to preserve high-order proximities of large scale graphs and capable of capturing the asymmetric transitivity.
Additionally, among the network, only very few of the users are labelled, which also poses a great challenge for only utilizing labeled data to achieve a satisfied performance on fraud detection.
The strength of deep clustering methods is to extract the useful representations from the data itself, rather than the structure of data, which receives scarce attention in representation learning.
Then, these weights are used in the weighted regression to improve the accuracy of estimation on the effect of each variable, thus help to improve the stability of prediction across unknown test data.
Mining graph data has become a popular research topic in computer science and has been widely studied in both academia and industry given the increasing amount of network data in the recent years.
Representation learning on a knowledge graph (KG) is to embed entities and relations of a KG into low-dimensional continuous vector spaces.
Our approach achieves macro disentanglement by inferring the high-level concepts associated with user intentions (e. g., to buy a shirt or a cellphone), while capturing the preference of a user regarding the different concepts separately.
To this end, we begin by investigating the theoretical connections between graph signal processing and graph embedding models in a principled way and formulate the graph embedding model as a general graph signal process with corresponding graph filter.
The experimental results demonstrate that NICO can well support the training of ConvNet model from scratch, and a batch balancing module can help ConvNets to perform better in Non-I. I. D.
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, there remain two unsolved challenges: i) there exist inconsistencies in cross-platform association due to platform-specific disparity, and ii) data from distinct platforms may have different semantic granularities.
Hashing techniques are in great demand for a wide range of real-world applications such as image retrieval and network compression.
In this paper, we propose a novel Deep Global Balancing Regression (DGBR) algorithm to jointly optimize a deep auto-encoder model for feature selection and a global balancing model for stable prediction across unknown environments.
Network embedding, which learns low-dimensional vector representation for nodes in the network, has attracted considerable research attention recently.
These hyper-networks pose great challenges to existing network embedding methods when the hyperedges are indecomposable, that is to say, any subset of nodes in a hyperedge cannot form another hyperedge.
Social and Information Networks
By setting a maximum tolerated error as a threshold, we can trigger SVD restart automatically when the margin exceeds this threshold. We prove that the time complexity of our method is linear with respect to the number of local dynamic changes, and our method is general across different types of dynamic networks.
Social and Information Networks
We then propose an out-of-sample embedding method to learn the embedding of a new class represented by a few samples through its visual analogy with base classes and derive the classification parameters for the new class.
However, this ideal assumption is often violated in real applications, where selection bias may arise between training and testing process.
While previous network embedding methods primarily preserve the microscopic structure, such as the first- and second-order proximities of nodes, the mesoscopic community structure, which is one of the most prominent feature of networks, is largely ignored.
As cascades are typical dynamic processes, it is always interesting and important to predict the cascade size at any time, or predict the time when a cascade will reach a certain size (e. g. an threshold for outbreak).
Social and Information Networks Physics and Society