Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search (MoreMNAS)
Fabricating neural models for a wide range of mobile devices demands for specific design of networks due to highly constrained resources. Both evolution algorithms (EA) and reinforced learning methods (RL) have been introduced to address Neural Architecture Search, distinct efforts to integrate both categories have also been proposed. However, these combinations usually concentrate on a single objective such as error rate of image classification. They also fail to harness the very benefits from both sides. In this paper, we present a new multi-objective oriented algorithm called MoreMNAS (Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search) by leveraging good virtues from both EA and RL. In particular, we incorporate a variant of multi-objective genetic algorithm NSGA-II, in which the search space is composed of various cells so that crossovers and mutations can be performed at the cell level. Moreover, reinforced control is mixed with random process to regulate arbitrary mutation, maintaining a delicate balance between exploration and exploitation. Therefore, not only does our method prevent the searched models from degrading during the evolution process, but it also makes better use of learned knowledge. Our preliminary experiments conducted in Super Resolution domain (SR) deliver rivalling models compared to some state-of-the-art methods with much less FLOPS. More results will be disclosed very soon …

Semantic Label Indexing, Neural Matching, and Efficient Ranking (SLINMER)
Extreme multi-label classification (XMC) aims to assign to an instance the most relevant subset of labels from a colossal label set. Due to modern applications that lead to massive label sets, the scalability of XMC has attracted much recent attention from both academia and industry. In this paper, we establish a three-stage framework to solve XMC efficiently, which includes 1) indexing the labels, 2) matching the instance to the relevant indices, and 3) ranking the labels from the relevant indices. This framework unifies many existing XMC approaches. Based on this framework, we propose a modular deep learning approach SLINMER: Semantic Label Indexing, Neural Matching, and Efficient Ranking. The label indexing stage of SLINMER can adopt different semantic label representations leading to different configurations of SLINMER. Empirically, we demonstrate that several individual configurations of SLINMER achieve superior performance than the state-of-the-art XMC approaches on several benchmark datasets. Moreover, by ensembling those configurations, SLINMER can achieve even better results. In particular, on a Wiki dataset with around 0.5 millions of labels, the precision@1 is increased from 61% to 67%. …

MASSES
We introduce MASSES, a simple evaluation metric for the task of Visual Question Answering (VQA). In its standard form, the VQA task is operationalized as follows: Given an image and an open-ended question in natural language, systems are required to provide a suitable answer. Currently, model performance is evaluated by means of a somehow simplistic metric: If the predicted answer is chosen by at least 3 human annotators out of 10, then it is 100% correct. Though intuitively valuable, this metric has some important limitations. First, it ignores whether the predicted answer is the one selected by the Majority (MA) of annotators. Second, it does not account for the quantitative Subjectivity (S) of the answers in the sample (and dataset). Third, information about the Semantic Similarity (SES) of the responses is completely neglected. Based on such limitations, we propose a multi-component metric that accounts for all these issues. We show that our metric is effective in providing a more fine-grained evaluation both on the quantitative and qualitative level. …

Interactive Growing Hierarchical SOM (interactive GHSOM)
Self Organizing Map is trained using unsupervised learning to produce a two-dimensional discretized representation of input space of the training cases. Growing Hierarchical SOM is an architecture which grows both in a hierarchical way representing the structure of data distribution and in a horizontal way representation the size of each individual maps. The control method of the growing degree of GHSOM by pruning off the redundant branch of hierarchy in SOM is proposed in this paper. Moreover, the interface tool for the proposed method called interactive GHSOM is developed. We discuss the computation results of Iris data by using the developed tool. …