Search Results for author:
Found 16 papers, 6 papers with code
Multi-Task Differential Privacy Under Distribution Skew
We study the problem of multi-task learning under user-level differential privacy, in which $n$ users contribute data to $m$ tasks, each involving a subset of users.
Attributing AUC-ROC to Analyze Binary Classifier Performance
This observation leads to a simple, efficient attribution technique for examples (example attributions), and for pairs of examples (pair attributions).
First is Better Than Last for Language Data Influence
However, we observe that since the activation connected to the last layer of weights contains "shared logic", the data influenced calculated via the last layer weights prone to a ``cancellation effect'', where the data influence of different examples have large magnitude that contradicts each other.
Reciprocity in Machine Learning
Are these contributions (outflows of influence) and benefits (inflows of influence) reciprocal?
The Penalty Imposed by Ablated Data Augmentation
There is a set of data augmentation techniques that ablate parts of the input at random.
Attribution in Scale and Space
Third, it eliminates the need for a 'baseline' parameter for Integrated Gradients [31] for perception tasks.
Estimating Training Data Influence by Tracing Gradient Descent
We introduce a method called TracIn that computes the influence of a training example on a prediction made by the model.
The many Shapley values for model explanation
In this paper, we use the axiomatic approach to study the differences between some of the many operationalizations of the Shapley value for attribution, and propose a technique called Baseline Shapley (BShap) that is backed by a proper uniqueness result.
How Important is a Neuron
Informally, the conductance of a hidden unit of a deep network is the flow of attribution via this hidden unit.
A Note about: Local Explanation Methods for Deep Neural Networks lack Sensitivity to Parameter Values
Local explanation methods, also known as attribution methods, attribute a deep network's prediction to its input (cf.
How Important Is a Neuron?
Informally, the conductance of a hidden unit of a deep network is the \emph{flow} of attribution via this hidden unit.
Did the Model Understand the Question?
Our strongest attacks drop the accuracy of a visual question answering model from $61. 1\%$ to $19\%$, and that of a tabular question answering model from $33. 5\%$ to $3. 3\%$.
It was the training data pruning too!
The large impact on the performance of the KDG model suggests that the pruning may be a useful pre-processing step in training other semantic parsers as well.
Axiomatic Attribution for Deep Networks
We study the problem of attributing the prediction of a deep network to its input features, a problem previously studied by several other works.
Explainable artificial intelligence
Interpretable Machine Learning
Gradients of Counterfactuals
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.
