Arrow Research search

Author name cluster

Jose Cadena

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers
1 author row

Possible papers

2

AAAI Conference 2018 Conference Paper

Graph Scan Statistics With Uncertainty

  • Jose Cadena
  • Arinjoy Basak
  • Anil Vullikanti
  • Xinwei Deng

Scan statistics is one of the most popular approaches for anomaly detection in spatial and network data. In practice, there are numerous sources of uncertainty in the observed data. However, most prior works have overlooked such uncertainty, which can affect the accuracy and inferences of such methods. In this paper, we develop the first systematic approach to incorporating uncertainty in scan statistics. We study two formulations for robust scan statistics, one based on the sample average approximation and the other using a max-min objective. We show that uncertainty significantly increases the computational complexity of these problems. Rigorous algorithms and efficient heuristics for both formulations are developed with justification of theoretical bounds. We evaluate our proposed methods on synthetic and real datasets, and we observe that our methods give significant improvement in the detection power as well as optimization objective, relative to a baseline.

PDF Details

AAAI Conference 2018 Conference Paper

Mining Heavy Temporal Subgraphs: Fast Algorithms and Applications

  • Jose Cadena
  • Anil Vullikanti

Anomaly detection is a fundamental problem in dynamic networks. In this paper, we study an approach for identifying anomalous subgraphs based on the Heaviest Dynamic Subgraph (HDS) problem. The HDS in a time-evolving edgeweighted graph consists of a pair containing a subgraph and sub-interval whose sum of edge weights is maximized. The HDS problem in a static graph is equivalent to the Prize Collecting Steiner Tree (PCST) problem with the Net-Worth objective—this is a very challenging problem, in general, and numerous heuristics have been proposed. Prior methods for the HDS problem use the PCST solution as a heuristic, and run in time quadratic in the size of the graph. As a result, they do not scale well to large instances. In this paper, we develop a new approach for the HDS problem, which combines rigorous algorithmic and practical techniques and has much better scalability. Our algorithm is able to extend to other variations of the HDS problem, such as the problem of finding multiple anomalous regions. We evaluate our algorithms in a diverse set of real and synthetic networks, and we find solutions with higher score and better detection power for anomalous events compared to earlier heuristics.

PDF Details