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.
Traditional semantic similarity models often fail to encapsulate the external context in which texts are situated. However, textual datasets generated on mobile platforms can help us build a truer representation of semantic similarity by introducing multimodal data. This is especially important in sparse datasets, making solely text-driven interpretation of context more difficult. In this paper, we develop new algorithms for building external features into sentence embeddings and semantic similarity scores. Then, we test them on embedding spaces on data from Twitter, using each tweet's time and geolocation to better understand its context. Ultimately, we show that applying PCA with eight components to the embedding space and appending multimodal features yields the best outcomes. This yields a considerable improvement over pure text-based approaches for discovering similar tweets. Our results suggest that our new algorithm can help improve semantic understanding in various settings.
We propose the Onto2Vec method, an approach to learn feature vectors for biological entities based on their annotations to biomedical ontologies. Our method can be applied to a wide range of bioinformatics research problems such as similarity-based prediction of interactions between proteins, classification of interaction types using supervised learning, or clustering.
This paper shows that the combination of knowledge and corpus-based word-to-word similarity measures can produce higher agreement with human judgment than any of the in-dividual measures. While this might be a predictable result, the paper provides insights about the circumstances under which a combination is productive and about the improve-ment levels that are to be expected. The experiments presented here were conducted using the word-to-word similarity measures included in SEMILAR, a freely available semantic similarity toolkit.