Qiqi Yan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Qiqi Yan has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Mukund Sundararajan
Google AI Healthcare Google Research Google Inc
4 shared publications - Ankur Taly
Google Inc
1 shared publication Kedar Dhamdhere
Google Inc, Mountain View, CA, USA
1 shared publication- Kedar Dhamdhere
University of Chicago
1 shared publication Kevin S. McCurley
Google, Inc, Mountain View, CA, USA
1 shared publication- Ralfi Nahmias
Google Inc, Mountain View, CA, USA
1 shared publication
Latest Publications
- Open Access
How Important Is a Neuron?
The problem of attributing a deep network's prediction to its \emph{input/base} features is well-studied. We introduce the notion of \emph{conductance} to extend the notion of attribution to the understanding the importance of \emph{hidden} units. Informally, the conductance of a hidden unit of a deep network is the \emph{flow} of attribution via this hidden unit. We use conductance to understand the importance of a hidden unit to the prediction for a specific input, or over a set of inputs. We evaluate the effectiveness of conductance in multiple ways, including theoretical properties, ablation studies, and a feature selection task. The empirical evaluations are done using the Inception network over ImageNet data, and a sentiment analysis network over reviews. In both cases, we demonstrate the effectiveness of conductance in identifying interesting insights about the internal workings of these networks.
Open AccessHow Important Is a Neuron?
The problem of attributing a deep network's prediction to its \emph{input/base} features is well-studied. We introduce the notion of \emph{conductance} to extend the notion of attribution to the understanding the importance of \emph{hidden} units. Informally, the conductance of a hidden unit of a deep network is the \emph{flow} of attribution via this hidden unit. We use conductance to understand the importance of a hidden unit to the prediction for a specific input, or over a set of inputs. We evaluate the effectiveness of conductance in multiple ways, including theoretical properties, ablation studies, and a feature selection task. The empirical evaluations are done using the Inception network over ImageNet data, and a sentiment analysis network over reviews. In both cases, we demonstrate the effectiveness of conductance in identifying interesting insights about the internal workings of these networks.
- Open Access
A Simple and Efficient MapReduce Algorithm for Data Cube Materialization
Data cube materialization is a classical database operator introduced in Gray et al.~(Data Mining and Knowledge Discovery, Vol.~1), which is critical for many analysis tasks. Nandi et al.~(Transactions on Knowledge and Data Engineering, Vol.~6) first studied cube materialization for large scale datasets using the MapReduce framework, and proposed a sophisticated modification of a simple broadcast algorithm to handle a dataset with a 216GB cube size within 25 minutes with 2k machines in 2012. We take a different approach, and propose a simple MapReduce algorithm which (1) minimizes the total number of copy-add operations, (2) leverages locality of computation, and (3) balances work evenly across machines. As a result, the algorithm shows excellent performance, and materialized a real dataset with a cube size of 35.0G tuples and 1.75T bytes in 54 minutes, with 0.4k machines in 2014.
Open AccessA Simple and Efficient MapReduce Algorithm for Data Cube Materialization
Data cube materialization is a classical database operator introduced in Gray et al.~(Data Mining and Knowledge Discovery, Vol.~1), which is critical for many analysis tasks. Nandi et al.~(Transactions on Knowledge and Data Engineering, Vol.~6) first studied cube materialization for large scale datasets using the MapReduce framework, and proposed a sophisticated modification of a simple broadcast algorithm to handle a dataset with a 216GB cube size within 25 minutes with 2k machines in 2012. We take a different approach, and propose a simple MapReduce algorithm which (1) minimizes the total number of copy-add operations, (2) leverages locality of computation, and (3) balances work evenly across machines. As a result, the algorithm shows excellent performance, and materialized a real dataset with a cube size of 35.0G tuples and 1.75T bytes in 54 minutes, with 0.4k machines in 2014.
- Open Access
- 7 March 2017
- Published by Association for Computing Machinery (ACM)
- p. 493-504
Analyza
We describe Analyza, a system that helps lay users explore data. Analyza has been used within two large real world systems. The first is a question-and-answer feature in a spreadsheet product. The second provides convenient access to a revenue/inventory database for a large sales force. Both user bases consist of users who do not necessarily have coding skills, demonstrating Analyza's ability to democratize access to data. We discuss the key design decisions in implementing this system. For instance, how to mix structured and natural language modalities, how to use conversation to disambiguate and simplify querying, how to rely on the ``semantics' of the data to compensate for the lack of syntactic structure, and how to efficiently curate the data.
- 7 March 2017
- Published by Association for Computing Machinery (ACM)
- p. 493-504
Open AccessAnalyza
We describe Analyza, a system that helps lay users explore data. Analyza has been used within two large real world systems. The first is a question-and-answer feature in a spreadsheet product. The second provides convenient access to a revenue/inventory database for a large sales force. Both user bases consist of users who do not necessarily have coding skills, demonstrating Analyza's ability to democratize access to data. We discuss the key design decisions in implementing this system. For instance, how to mix structured and natural language modalities, how to use conversation to disambiguate and simplify querying, how to rely on the ``semantics' of the data to compensate for the lack of syntactic structure, and how to efficiently curate the data.
- Open Access
Gradients of Counterfactuals
Gradients have been used to quantify feature importance in machine learning models. Unfortunately, in nonlinear deep networks, not only individual neurons but also the whole network can saturate, and as a result an important input feature can have a tiny gradient. We study various networks, and observe that this phenomena is indeed widespread, across many inputs. We propose to examine interior gradients, which are gradients of counterfactual inputs constructed by scaling down the original input. We apply our method to the GoogleNet architecture for object recognition in images, as well as a ligand-based virtual screening network with categorical features and an LSTM based language model for the Penn Treebank dataset. We visualize how interior gradients better capture feature importance. Furthermore, interior gradients are applicable to a wide variety of deep networks, and have the attribution property that the feature importance scores sum to the the prediction score. Best of all, interior gradients can be computed just as easily as gradients. In contrast, previous methods are complex to implement, which hinders practical adoption.
Open AccessGradients of Counterfactuals
Gradients have been used to quantify feature importance in machine learning models. Unfortunately, in nonlinear deep networks, not only individual neurons but also the whole network can saturate, and as a result an important input feature can have a tiny gradient. We study various networks, and observe that this phenomena is indeed widespread, across many inputs. We propose to examine interior gradients, which are gradients of counterfactual inputs constructed by scaling down the original input. We apply our method to the GoogleNet architecture for object recognition in images, as well as a ligand-based virtual screening network with categorical features and an LSTM based language model for the Penn Treebank dataset. We visualize how interior gradients better capture feature importance. Furthermore, interior gradients are applicable to a wide variety of deep networks, and have the attribution property that the feature importance scores sum to the the prediction score. Best of all, interior gradients can be computed just as easily as gradients. In contrast, previous methods are complex to implement, which hinders practical adoption.