• Publications
  • Influence
Graph Minors
For a given graph G and integers b, f ≥ 0, let S be a subset of vertices of G of size b + 1 such that the subgraph of G induced by S is connected and S can be separated from other vertices of G byExpand
Representation Learning on Graphs with Jumping Knowledge Networks
This work explores an architecture -- jumping knowledge (JK) networks -- that flexibly leverages, for each node, different neighborhood ranges to enable better structure-aware representation in graphs. Expand
Scalable similarity search for SimRank
This paper proposes a very fast and scalable SimRank-based similarity search problem, and establishes a Monte-Carlo based algorithm to compute a single pair SimRank score s(u,v), which is based on the random-walk interpretation of the linear recursive formula. Expand
Fast and Accurate Influence Maximization on Large Networks with Pruned Monte-Carlo Simulations
The proposed method is a Monte-Carlo-simulation-based method, and thus it consistently produces solutions of high quality with the theoretical guarantee, and runs as fast as other state-of-the-art methods, and can be applied to large networks of the day. Expand
The disjoint paths problem in quadratic time
The time complexity of all the algorithms with the most expensive part depending on Robertson and [email protected]?s algorithm can be improved to O(n^2), for example, the membership testing for minor-closed class of graphs. Expand
Estimating Local Intrinsic Dimensionality
This paper is concerned with the estimation of a local measure of intrinsic dimensionality recently proposed by Houle, and several estimators of local ID are proposed and analyzed based on extreme value theory, using maximum likelihood estimation (MLE), the method of moments, probability weighted moments, and regularly varying functions (RV). Expand
What Can Neural Networks Reason About?
This framework offers an explanation for the empirical success of popular reasoning models, and suggests their limitations, and unify seemingly different reasoning tasks via the lens of a powerful algorithmic paradigm, dynamic programming (DP). Expand
Shortest-path queries for complex networks: exploiting low tree-width outside the core
Two new methods for efficient shortest-path query processing are presented, including the exact and the hybrid method, which provides an improved tradeoff between space and accuracy and the methods for graphs with small tree-width. Expand
Unsupervised Cross-Domain Word Representation Learning
The proposed method significantly outperforms competitive baselines including the state-of-the-art domain-insensitive word representations, and reports best sentiment classification accuracies for all domain-pairs in a benchmark dataset. Expand
Optimal Budget Allocation: Theoretical Guarantee and Efficient Algorithm
This framework includes Alon et al.'s model, even with a competitor and with cost, and gives a faster (1 - 1/e)-approximation algorithm, which allows us to implement the authors' algorithm up to almost 10M edges. Expand