You need to log in to edit.

You can create a new account if you don't have one.

Or, discuss a change on Slack.

You can create a new account if you don't have one.

Or, discuss a change on Slack.

no code implementations • 31 Aug 2022 • Andrew Bai, Chih-Kuan Yeh, Pradeep Ravikumar, Neil Y. C. Lin, Cho-Jui Hsieh

We showed that for a general (potentially non-linear) concept, we can mathematically evaluate how a small change of concept affecting the model's prediction, which leads to an extension of gradient-based interpretation to the concept space.

1 code implementation • 2 Mar 2022 • Che-Ping Tsai, Chih-Kuan Yeh, Pradeep Ravikumar

We show that by additionally requiring the faithful interaction indices to satisfy interaction-extensions of the standard individual Shapley axioms (dummy, symmetry, linearity, and efficiency), we obtain a unique Faithful Shapley Interaction index, which we denote Faith-Shap, as a natural generalization of the Shapley value to interactions.

no code implementations • 25 Feb 2022 • Chih-Kuan Yeh, Been Kim, Pradeep Ravikumar

We start by introducing concept explanations including the class of Concept Activation Vectors (CAV) which characterize concepts using vectors in appropriate spaces of neural activations, and discuss different properties of useful concepts, and approaches to measure the usefulness of concept vectors.

1 code implementation • 24 Feb 2022 • Chih-Kuan Yeh, Ankur Taly, Mukund Sundararajan, Frederick Liu, Pradeep Ravikumar

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.

no code implementations • 24 Feb 2022 • Chih-Kuan Yeh, Kuan-Yun Lee, Frederick Liu, Pradeep Ravikumar

We formalize the desiderata of value functions that respect both the model and the data manifold in a set of axioms and are robust to perturbation on off-manifold regions, and show that there exists a unique value function that satisfies these axioms, which we term the Joint Baseline value function, and the resulting Shapley value the Joint Baseline Shapley (JBshap), and validate the effectiveness of JBshap in experiments.

no code implementations • ICLR 2021 • Cheng-Yu Hsieh, Chih-Kuan Yeh, Xuanqing Liu, Pradeep Ravikumar, Seungyeon Kim, Sanjiv Kumar, Cho-Jui Hsieh

In this paper, we establish a novel set of evaluation criteria for such feature based explanations by robustness analysis.

1 code implementation • ICLR 2020 • Biswajit Paria, Chih-Kuan Yeh, Ian E. H. Yen, Ning Xu, Pradeep Ravikumar, Barnabás Póczos

Deep representation learning has become one of the most widely adopted approaches for visual search, recommendation, and identification.

1 code implementation • NeurIPS 2019 • Chih-Kuan Yeh, Cheng-Yu Hsieh, Arun Suggala, David I. Inouye, Pradeep K. Ravikumar

We analyze optimal explanations with respect to both these measures, and while the optimal explanation for sensitivity is a vacuous constant explanation, the optimal explanation for infidelity is a novel combination of two popular explanation methods.

2 code implementations • NeurIPS 2020 • Chih-Kuan Yeh, Been Kim, Sercan O. Arik, Chun-Liang Li, Tomas Pfister, Pradeep Ravikumar

Next, we propose a concept discovery method that aims to infer a complete set of concepts that are additionally encouraged to be interpretable, which addresses the limitations of existing methods on concept explanations.

no code implementations • 25 Sep 2019 • Chih-Kuan Yeh, Been Kim, Sercan Arik, Chun-Liang Li, Pradeep Ravikumar, Tomas Pfister

Next, we propose a concept discovery method that considers two additional constraints to encourage the interpretability of the discovered concepts.

no code implementations • ICLR 2019 • Chih-Kuan Yeh, Ian E. H. Yen, Hong-You Chen, Chun-Pei Yang, Shou-De Lin, Pradeep Ravikumar

State-of-the-art deep neural networks (DNNs) typically have tens of millions of parameters, which might not fit into the upper levels of the memory hierarchy, thus increasing the inference time and energy consumption significantly, and prohibiting their use on edge devices such as mobile phones.

2 code implementations • 27 Jan 2019 • Chih-Kuan Yeh, Cheng-Yu Hsieh, Arun Sai Suggala, David I. Inouye, Pradeep Ravikumar

We analyze optimal explanations with respect to both these measures, and while the optimal explanation for sensitivity is a vacuous constant explanation, the optimal explanation for infidelity is a novel combination of two popular explanation methods.

no code implementations • ICLR 2019 • Chih-Kuan Yeh, Jianshu Chen, Chengzhu Yu, Dong Yu

We consider the problem of training speech recognition systems without using any labeled data, under the assumption that the learner can only access to the input utterances and a phoneme language model estimated from a non-overlapping corpus.

1 code implementation • NeurIPS 2018 • Chih-Kuan Yeh, Joon Sik Kim, Ian E. H. Yen, Pradeep Ravikumar

We propose to explain the predictions of a deep neural network, by pointing to the set of what we call representer points in the training set, for a given test point prediction.

no code implementations • ECCV 2018 • Hong-Min Chu, Chih-Kuan Yeh, Yu-Chiang Frank Wang

In order to train learning models for multi-label classification (MLC), it is typically desirable to have a large amount of fully annotated multi-label data.

1 code implementation • CVPR 2018 • Chung-Wei Lee, Wei Fang, Chih-Kuan Yeh, Yu-Chiang Frank Wang

In this paper, we propose a novel deep learning architecture for multi-label zero-shot learning (ML-ZSL), which is able to predict multiple unseen class labels for each input instance.

1 code implementation • 18 Jul 2017 • Shang-Fu Chen, Yi-Chen Chen, Chih-Kuan Yeh, Yu-Chiang Frank Wang

In this paper, we propose the joint learning attention and recurrent neural network (RNN) models for multi-label classification.

1 code implementation • 3 Jul 2017 • Chih-Kuan Yeh, Wei-Chieh Wu, Wei-Jen Ko, Yu-Chiang Frank Wang

Multi-label classification is a practical yet challenging task in machine learning related fields, since it requires the prediction of more than one label category for each input instance.

no code implementations • 7 Jun 2017 • Chih-Kuan Yeh, Yao-Hung Hubert Tsai, Yu-Chiang Frank Wang

In other words, our GDVM casts the supervised learning task as a generative learning process, with data discrimination to be jointly exploited for improved classification.

no code implementations • 12 Jul 2016 • Chih-Kuan Yeh, Hsuan-Tien Lin

Existing artificial intelligence systems for bridge bidding rely on and are thus restricted by human-designed bidding systems or features.

Cannot find the paper you are looking for? You can
Submit a new open access paper.

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.