Collaborating Authors

Learnable Parameter Similarity Machine Learning

Most of the existing approaches focus on specific visual tasks while ignoring the relations between them. Estimating task relation sheds light on the learning of high-order semantic concepts, e.g., transfer learning. How to reveal the underlying relations between different visual tasks remains largely unexplored. In this paper, we propose a novel \textbf{L}earnable \textbf{P}arameter \textbf{S}imilarity (\textbf{LPS}) method that learns an effective metric to measure the similarity of second-order semantics hidden in trained models. LPS is achieved by using a second-order neural network to align high-dimensional model parameters and learning second-order similarity in an end-to-end way. In addition, we create a model set called ModelSet500 as a parameter similarity learning benchmark that contains 500 trained models. Extensive experiments on ModelSet500 validate the effectiveness of the proposed method. Code will be released at \url{}.

Convolutional Set Matching for Graph Similarity Machine Learning

We introduce GSimCNN (Graph Similarity Computation via Convolutional Neural Networks) for predicting the similarity score between two graphs. As the core operation of graph similarity search, pairwise graph similarity computation is a challenging problem due to the NPhard nature of computing many graph distance/similarity metrics. We demonstrate our model using the Graph Edit Distance (GED) [2] as the example metric. It is defined as the number of edit operations in the optimal alignments that transform one graph into the other, where an edit operation can be an insertion or a deletion of a node/edge, or relabelling of a node. It is NPhard [3] and costly to compute in practice [4]. The key idea is to turn the pairwise graph distance computation problem into a learning problem.

DNN-based Speaker Embedding Using Subjective Inter-speaker Similarity for Multi-speaker Modeling in Speech Synthesis Machine Learning

This paper proposes novel algorithms for speaker embedding using subjective inter-speaker similarity based on deep neural networks (DNNs). Although conventional DNN-based speaker embedding such as a $d$-vector can be applied to multi-speaker modeling in speech synthesis, it does not correlate with the subjective inter-speaker similarity and is not necessarily appropriate speaker representation for open speakers whose speech utterances are not included in the training data. We propose two training algorithms for DNN-based speaker embedding model using an inter-speaker similarity matrix obtained by large-scale subjective scoring. One is based on similarity vector embedding and trains the model to predict a vector of the similarity matrix as speaker representation. The other is based on similarity matrix embedding and trains the model to minimize the squared Frobenius norm between the similarity matrix and the Gram matrix of $d$-vectors, i.e., the inter-speaker similarity derived from the $d$-vectors. We crowdsourced the inter-speaker similarity scores of 153 Japanese female speakers, and the experimental results demonstrate that our algorithms learn speaker embedding that is highly correlated with the subjective similarity. We also apply the proposed speaker embedding to multi-speaker modeling in DNN-based speech synthesis and reveal that the proposed similarity vector embedding improves synthetic speech quality for open speakers whose speech utterances are unseen during the training.

Representation Similarity Analysis for Efficient Task taxonomy & Transfer Learning Artificial Intelligence

Transfer learning is widely used in deep neural network models when there are few labeled examples available. The common approach is to take a pre-trained network in a similar task and finetune the model parameters. This is usually done blindly without a pre-selection from a set of pre-trained models, or by finetuning a set of models trained on different tasks and selecting the best performing one by cross-validation. We address this problem by proposing an approach to assess the relationship between visual tasks and their task-specific models. Our method uses Representation Similarity Analysis (RSA), which is commonly used to find a correlation between neuronal responses from brain data and models. With RSA we obtain a similarity score among tasks by computing correlations between models trained on different tasks. Our method is efficient as it requires only pre-trained models, and a few images with no further training. We demonstrate the effectiveness and efficiency of our method for generating task taxonomy on Taskonomy dataset. We next evaluate the relationship of RSA with the transfer learning performance on Taskonomy tasks and a new task: Pascal VOC semantic segmentation. Our results reveal that models trained on tasks with higher similarity score show higher transfer learning performance. Surprisingly, the best transfer learning result for Pascal VOC semantic segmentation is not obtained from the pre-trained model on semantic segmentation, probably due to the domain differences, and our method successfully selects the high performing models.


AAAI Conferences

Community detection on social media is a classic and challenging task. In this paper, we study the problem of detecting communities by combining social relations and user generated content in social networks. We propose a nonnegative matrix tri-factorization (NMTF) based clustering framework with three types of graph regularization. The NMTF based clustering framework can combine the relations and content seamlessly and the graph regularization can capture user similarity, message similarity and user interaction explicitly. In order to design regularization components, we further exploit user similarity and message similarity in social networks. A unified optimization problem is proposed by integrating the NMTF framework and the graph regularization. Then we derive an iterative learning algorithm for this optimization problem. Extensive experiments are conducted on three real-world data sets and the experimental results demonstrate the effectiveness of the proposed method.