Goto

Collaborating Authors

Xu, Ke


DA-HGT: Domain Adaptive Heterogeneous Graph Transformer

arXiv.org Machine Learning

Domain adaptation using graph networks is to learn labeldiscriminative and network-invariant node embeddings by sharing graph parameters. Most existing works focus on domain adaptation of homogeneous networks, and just a few works begin to study heterogeneous cases that only consider the shared node types but ignore the private node types in individual networks. However, for a given source and target heterogeneous networks, they generally contain shared and private node types, where private types bring an extra challenge for graph domain adaptation. In this paper, we investigate Heterogeneous Information Networks (HINs) with partial shared node types and propose a novel domain adaptive heterogeneous graph transformer (DA-HGT) to handle the domain shift between them. DA-HGT can not only align the distributions of identical-type nodes and edges in two HINs but also make full use of different-type nodes and edges to improve the performance of knowledge transfer. Extensive experiments on several datasets demonstrate that DA-HGT can outperform state-of-the-art methods in various domain adaptation tasks across heterogeneous networks. Figure 1: Challenges on domain adaptation across HINs.


Exact Phase Transitions of Model RB with Slower-Growing Domains

arXiv.org Artificial Intelligence

The study of random constraint satisfaction problems (CSPs) has received tremendous ideas from combinatorics, computer science and statistical physics. Random CSPs contain a large set of variables which interact through a large set of constraints, where each variable ranges over a domain and a configuration (solution) to all the variables should satisfy all of the constraints. A fundamental question in the study of random CSPs is the average-case computational complexity of solving ensembles of CSPs. Great amount of theoretical and algorithmic work has been devoted to establish and locate the satisfiability threshold, and studies show that complexity attains the maximum at the SAT-UNSAT transition. Many of the studied CSP models (such as random k-SAT, graph coloring) have fixed domain size, constraint length, and the number of constraints is linear compared with the number of variables. In recent years, a lot of attention has been paid to the study of CSPs with growing domains or constraint length ([13, 7, 4, 5]).


Towards Ground Truth Explainability on Tabular Data

arXiv.org Machine Learning

In data science, there is a long history of using synthetic data for method development, feature selection and feature engineering. Our current interest in synthetic data comes from recent work in explainability. Today's datasets are typically larger and more complex - requiring less interpretable models. In the setting of \textit{post hoc} explainability, there is no ground truth for explanations. Inspired by recent work in explaining image classifiers that does provide ground truth, we propose a similar solution for tabular data. Using copulas, a concise specification of the desired statistical properties of a dataset, users can build intuition around explainability using controlled data sets and experimentation. The current capabilities are demonstrated on three use cases: one dimensional logistic regression, impact of correlation from informative features, impact of correlation from redundant variables.


Learning Influence Functions from Incomplete Observations

Neural Information Processing Systems

We study the problem of learning influence functions under incomplete observations of node activations. Incomplete observations are a major concern as most (online and real-world) social networks are not fully observable. We establish both proper and improper PAC learnability of influence functions under randomly missing observations. Proper PAC learnability under the Discrete-Time Linear Threshold (DLT) and Discrete-Time Independent Cascade (DIC) models is established by reducing incomplete observations to complete observations in a modified graph. Our improper PAC learnability result applies for the DLT and DIC models as well as the Continuous-Time Independent Cascade (CIC) model.


Active Matting

Neural Information Processing Systems

Image matting is an ill-posed problem. It requires a user input trimap or some strokes to obtain an alpha matte of the foreground object. A fine user input is essential to obtain a good result, which is either time consuming or suitable for experienced users who know where to place the strokes. In this paper, we explore the intrinsic relationship between the user input and the matting algorithm to address the problem of where and when the user should provide the input. Our aim is to discover the most informative sequence of regions for user input in order to produce a good alpha matte with minimum labeling efforts. To this end, we propose an active matting method with recurrent reinforcement learning. The proposed framework involves human in the loop by sequentially detecting informative regions for trivial human judgement. Comparing to traditional matting algorithms, the proposed framework requires much less efforts, and can produce satisfactory results with just 10 regions. Through extensive experiments, we show that the proposed model reduces user efforts significantly and achieves comparable performance to dense trimaps in a user-friendly manner. We further show that the learned informative knowledge can be generalized across different matting algorithms.


Active Matting

Neural Information Processing Systems

Image matting is an ill-posed problem. It requires a user input trimap or some strokes to obtain an alpha matte of the foreground object. A fine user input is essential to obtain a good result, which is either time consuming or suitable for experienced users who know where to place the strokes. In this paper, we explore the intrinsic relationship between the user input and the matting algorithm to address the problem of where and when the user should provide the input. Our aim is to discover the most informative sequence of regions for user input in order to produce a good alpha matte with minimum labeling efforts. To this end, we propose an active matting method with recurrent reinforcement learning. The proposed framework involves human in the loop by sequentially detecting informative regions for trivial human judgement. Comparing to traditional matting algorithms, the proposed framework requires much less efforts, and can produce satisfactory results with just 10 regions. Through extensive experiments, we show that the proposed model reduces user efforts significantly and achieves comparable performance to dense trimaps in a user-friendly manner. We further show that the learned informative knowledge can be generalized across different matting algorithms.


Solving Generalized Column Subset Selection With Heuristic Search

AAAI Conferences

We address the problem of approximating a matrix by the linear combination of a column sparse matrix and a low rank matrix. Two variants of a heuristic search algorithm are described. The first produces an optimal solution but may be slow, as these problems are believed to be NP-hard. The second is much faster, but only guarantees a suboptimal solution. The quality of the approximation and the optimality criterion can be specified in terms of unitarily invariant norms.


Cleaning the Null Space: A Privacy Mechanism for Predictors

AAAI Conferences

In standard machine learning and regression setting feature values are used to predict some desired information. The privacy challenge considered here is to prevent an adversary from using available feature values to predict confidential information that one wishes to keep secret. We show that this can sometimes be achieved with almost no effect on the qual- ity of predicting desired information. We describe two algorithms aimed at providing such privacy when the predictors have a linear operator in the first stage. The desired effect can be achieved by zeroing out feature components in the approximate null space of the linear operator.


Enhancing the Privacy of Predictors

AAAI Conferences

The privacy challenge considered here is to prevent an adversary from using available feature values to predict confi- dential information. We propose an algorithm providing such privacy for predictors that have a linear operator in the first stage. Privacy is achieved by zeroing out feature components in the approximate null space of the linear operator. We show that this has little effect on predicting desired information.


Learning Influence Functions from Incomplete Observations

Neural Information Processing Systems

We study the problem of learning influence functions under incomplete observations of node activations. Incomplete observations are a major concern as most (online and real-world) social networks are not fully observable. We establish both proper and improper PAC learnability of influence functions under randomly missing observations. Proper PAC learnability under the Discrete-Time Linear Threshold (DLT) and Discrete-Time Independent Cascade (DIC) models is established by reducing incomplete observations to complete observations in a modified graph. Our improper PAC learnability result applies for the DLT and DIC models as well as the Continuous-Time Independent Cascade (CIC) model. It is based on a parametrization in terms of reachability features, and also gives rise to an efficient and practical heuristic. Experiments on synthetic and real-world datasets demonstrate the ability of our method to compensate even for a fairly large fraction of missing observations.