Graph neural networks (GNNs), which learn the node representations by recursively aggregating information from its neighbors, have become a predominant computational tool in many domains.
In view of those, we present the first fair and reproducible benchmark dedicated to assessing the "tricks" of training deep GNNs.
The pipeline language is quite general so that we can easily enrich AutoVideo with algorithms for various other video-related tasks in the future.
To this end, we analyze the bottleneck of deep GNNs by leveraging the Dirichlet energy of node embeddings, and propose a generalizable principle to guide the training of deep GNNs.
Our experiments demonstrate a significant improvement in the realism of the generated graph structures, typically by 1-2 orders of magnitude of graph structure metrics, compared to leading graph VAEand GAN models.
This process not only requires a lot of instance-level annotations for sensitive attributes, it also does not guarantee that all fairness sensitive information has been removed from the encoder.
To address these limitations, we propose a Model-based Counterfactual Synthesizer (MCS) framework for interpreting machine learning models.
Games are abstractions of the real world, where artificial agents learn to compete and cooperate with other agents.
However, the attribution problem has not been well-defined, which lacks a unified guideline to the contribution assignment process.
Motivated by the success of disentangled representation learning in computer vision, we study the possibility of learning semantic-rich time-series representations, which remains unexplored due to three main challenges: 1) sequential data structure introduces complex temporal correlations and makes the latent representations hard to interpret, 2) sequential models suffer from KL vanishing problem, and 3) interpretable semantic concepts for time-series often rely on multiple factors instead of individuals.
The basic idea is to learn a source signal by back-propagation such that the mutual information between input and output should be as much as possible preserved in the mutual information between input and the source signal.
We validate in experiments that the relative gain from automated data augmentation in test accuracy is highly correlated to Variance Diversity.
These two observations are further employed to formulate a measurement which can quantify the shortcut degree of each training sample.
Our sparse-interest module can adaptively infer a sparse set of concepts for each user from the large concept pool and output multiple embeddings accordingly.
It segments the overall long behavior sequence into a series of sub-sequences, then trains the model and maintains a set of memory blocks to preserve long-term interests of users.
Unfortunately, methods based on intrinsic rewards often fall short in procedurally-generated environments, where a different environment is generated in each episode so that the agent is not likely to visit the same state more than once.
With the wide use of deep neural networks (DNN), model interpretability has become a critical concern, since explainable decisions are preferred in high-stake scenarios.
Differentiable NAS with supernets that encompass all potential architectures in a large graph cuts down search overhead to few GPU days or less.
Motivated by the observation, in this paper, we propose to investigate the interaction detection problem from a novel topological perspective by analyzing the connectivity in neural networks.
In this paper, we introduce DSN (Deep Serial Number), a new watermarking approach that can prevent the stolen model from being deployed by unauthorized parties.
In order to make dimensionality reduction effective for high-dimensional data embedding nonlinear low-dimensional manifold, it is understood that some sort of geodesic distance metric should be used to discriminate the data samples.
Detecting statistical interactions between input features is a crucial and challenging task.
We present TODS, an automated Time Series Outlier Detection System for research and industrial applications.
Specifically, existing strategies have been focused on making the top instances more likely to be anomalous based on the feedback.
Recent years have witnessed an increasing number of interpretation methods being developed for improving transparency of NLP models.
Different from previous work, in our model, factor discovery and representation learning are simultaneously conducted, and we are able to handle extra attribute information and knowledge.
Attribution methods have been developed to understand the decision-making process of machine learning models, especially deep neural networks, by assigning importance scores to individual features.
Combating fake news and misinformation propagation is a challenging task in the post-truth era.
Click-Through Rate (CTR) prediction is one of the most important machine learning tasks in recommender systems, driving personalized experience for billions of consumers.
To address the need, we present AutoRec, an open-source automated machine learning (AutoML) platform extended from the TensorFlow ecosystem and, to our knowledge, the first framework to leverage AutoML for model search and hyperparameter tuning in deep recommendation models.
It is a challenging task to develop an effective aggregation strategy for each node, given complex graphs and sparse features.
Outlier detection is an important data mining task with numerous practical applications such as intrusion detection, credit card fraud detection, and video surveillance.
Our results demonstrate that the occurrence of overfitting is positively correlated with the increase of model complexity during training.
In this paper, we investigate a specific security problem called trojan attack, which aims to attack deployed DNN systems relying on the hidden trigger patterns inserted by malicious hackers.
Image captioning has made substantial progress with huge supporting image collections sourced from the web.
Graph neural networks (GNNs), which learn the representation of a node by aggregating its neighbors, have become an effective computational tool in downstream applications.
In this work, we introduce dual policy distillation(DPD), a student-student framework in which two learners operate on the same environment to explore different perspectives of the environment and extract knowledge from each other to enhance their learning.
Furthermore, our experimental results indicate that the generated graphs can provide guidance on how to improve the trained GNNs.
On the other hand, iCapsNets explore a novel way to explain the model's general behavior, achieving global interpretability.
In this paper, we review recent work on adversarial attacks and defenses, particularly from the perspective of machine learning interpretation.
In this work, we investigate the problem of hashing with graph neural networks (GNNs) for high quality retrieval, and propose a simple yet effective discrete representation learning framework to jointly learn continuous and discrete codes.
To further improve the graph representation learning ability, hierarchical GNN has been explored.
The goal of RLCard is to bridge reinforcement learning and imperfect information games, and push forward the research of reinforcement learning in domains with multiple agents, large state and action space, and sparse reward.
Recently, increasing attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the network makes specific decisions.
We introduce a new model-agnostic explanation technique which explains the prediction of any classifier called CLE.
Neural architecture search (NAS) is gaining more and more attention in recent years due to its flexibility and remarkable capability to reduce the burden of neural network design.
The analysis further shows that LAE outperforms the state-of-the-arts by 6. 52%, 12. 03%, and 3. 08% respectively on three deepfake detection tasks in terms of generalization accuracy on previously unseen manipulations.
First, the search space of GNN is different from the ones in existing NAS work.
Ranked #31 on Node Classification on Cora
Recent explainability related studies have shown that state-of-the-art DNNs do not always adopt correct evidences to make decisions.
To this end, we propose a novel deep structured anomaly detection framework to identify the cross-modal anomalies embedded in the data.
Automated machine learning (AutoML) aims to find optimal machine learning solutions automatically given a machine learning problem.
Interpretable Machine Learning (IML) has become increasingly important in many real-world applications, such as autonomous cars and medical diagnosis, where explanations are significantly preferred to help people better understand how machine learning systems work and further enhance their trust towards systems.
In this demo paper, we present the XFake system, an explainable fake news detector that assists end-users to identify news credibility.
Experience replay enables reinforcement learning agents to memorize and reuse past experiences, just as humans replay memories for the situation at hand.
More and more AI services are provided through APIs on cloud where predictive models are hidden behind APIs.
To bridge the gap, in this paper, we propose a Coupled Variational Recurrent Collaborative Filtering (CVRCF) framework based on the idea of Deep Bayesian Learning to handle the streaming recommendation problem.
Attributed graphs, which contain rich contextual features beyond just network structure, are ubiquitous and have been observed to benefit various network analytics applications.
Network embedding models are powerful tools in mapping nodes in a network into continuous vector-space representations in order to facilitate subsequent tasks such as classification and link prediction.
REAT decomposes the final prediction of a RNN into additive contribution of each word in the input text.
Experiments on real-world multi-label image classification and ranking problems demonstrate the effectiveness of our proposed frameworks and provide insights of the vulnerability of multi-label deep learning models under diverse targeted attacking strategies.
Moreover, the learned vector representations are not in a smooth space since the values can only be integers.
Ranked #8 on Graph Classification on PTC
Interpretable machine learning tackles the important problem that humans cannot understand the behaviors of complex machine learning models and how these models arrive at a particular decision.
In this paper, we propose a novel framework enabling Bayesian optimization to guide the network morphism for efficient neural architecture search.
While deep neural networks (DNN) have become an effective computational tool, the prediction results are often criticized by the lack of interpretability, which is essential in many real-world applications such as health informatics.
Strong intelligent machines powered by deep neural networks are increasingly deployed as black boxes to make decisions in risk-sensitive domains, such as finance and medical.
Outlier detection plays an essential role in many data-driven applications to identify isolated instances that are different from the majority.
In order to answer these kinds of questions, we attempt to model human sense of style compatibility in this paper.
When it comes to model the key factor in collaborative filtering -- the interaction between user and item features, they still resorted to matrix factorization and applied an inner product on the latent features of users and items.
Ranked #1 on Recommendation Systems on Pinterest
To our best knowledge, we are the first to tackle this problem with the following two challenges: (1) the inherently correlated network and node attributes could be noisy and incomplete, it necessitates a robust consensus representation to capture their individual properties and correlations; (2) the embedding learning needs to be performed in an online fashion to adapt to the changes accordingly.
With the agreement of my coauthors, I Zhangyang Wang would like to withdraw the manuscript "Stacked Approximated Regression Machine: A Simple Deep Learning Approach".