Feature representations from pre-trained deep neural networks have been known to exhibit excellent generalization and utility across a variety of related tasks. Fine-tuning is by far the simplest and most widely used approach that seeks to exploit and adapt these feature representations to novel tasks with limited data. Despite the effectiveness of fine-tuning, it is often sub-optimal and requires very careful optimization to prevent severe over-fitting to small datasets. The problem of sub-optimality and overfitting, is due in part to the large number of parameters used in a typical deep convolutional neural network. To address these problems, we propose a simple yet effective regularization method for fine-tuning pre-trained deep networks for the task of k-shot learning. To prevent overfitting, our key strategy is to cluster the model parameters while ensuring intra-cluster similarity and inter-cluster diversity of the parameters, effectively regularizing the dimensionality of the parameter search space. In particular, we identify groups of neurons within each layer of a deep network that shares similar activation patterns. When the network is to be fine-tuned for a classification task using only k examples, we propagate a single gradient to all of the neuron parameters that belong to the same group. The grouping of neurons is non-trivial as neuron activations depend on the distribution of the input data. To efficiently search for optimal groupings conditioned on the input data, we propose a reinforcement learning search strategy using recurrent networks to learn the optimal group assignments for each network layer. Experimental results show that our method can be easily applied to several popular convolutional neural networks and improve upon other state-of-the-art fine-tuning based k-shot learning strategies by more than 10%.

Huge volumes of opinion-rich data is user-generated in social media at an unprecedented rate, easing the analysis of individual and public sentiments. Sentiment analysis has shown to be useful in probing and understanding emotions, expressions and attitudes in the text. However, the distinct characteristics of social media data present challenges to traditional sentiment analysis. First, social media data is often noisy, incomplete and fast-evolved which necessitates the design of a sophisticated learning model. Second, sentiment labels are hard to collect which further exacerbates the problem by not being able to discriminate sentiment polarities. Meanwhile, opportunities are also unequivocally presented. Social media contains rich sources of sentiment signals in textual terms and user interactions, which could be helpful in sentiment analysis. While there are some attempts to leverage implicit sentiment signals in positive user interactions, little attention is paid on signed social networks with both positive and negative links. The availability of signed social networks motivates us to investigate if negative links also contain useful sentiment signals. In this paper, we study a novel problem of unsupervised sentiment analysis with signed social networks. In particular, we incorporate explicit sentiment signals in textual terms and implicit sentiment signals from signed social networks into a coherent model SignedSenti for unsupervised sentiment analysis. Empirical experiments on two real-world datasets corroborate its effectiveness.

In this paper we present a novel geometric method for the problem of global pairwise alignment of protein-protein interaction (PPI) networks. A PPI network can be viewed as a node-edge graph and its alignment often needs to solve some generalized version of the subgraph isomorphism problem which is notoriously challenging and NP-hard. All existing research has focused on designing algorithms with good practical performance. In this paper we propose a two-step algorithm for the global pairwise PPI network alignment which consists of a Geometric Step and an MCMF Step. Our algorithm first applies a graph embedding technique that preserves the topological structure of the original PPI networks and maps the problem from graph domain to geometric domain, and computes a rigid transformation for one of the embedded PPI networks so as to minimize its Earth Mover's Distance (EMD) to the other PPI network. It then solves a Min-Cost Max-Flow problem using the (scaled) inverse of sequence similarity scores as edge weight. By using the flow values from the two steps (i.e., EMD and Min-Cost Max-Flow) as the matching scores, we are able to combine the two matching results to obtain the desired alignment. Unlike other popular alignment algorithms which are either greedy or incremental, our algorithm globally optimizes the problem to yield an alignment with better quality.

Data classification and tag recommendation are both important and challenging tasks in social media. These two tasks are often considered independently and most efforts have been made to tackle them separately. However, labels in data classification and tags in tag recommendation are inherently related. For example, a Youtube video annotated with NCAA, stadium, pac12 is likely to be labeled as football, while a video/image with the class label of coast is likely to be tagged with beach, sea, water and sand. The existence of relations between labels and tags motivates us to jointly perform classification and tag recommendation for social media data in this paper. In particular, we provide a principled way to capture the relations between labels and tags, and propose a novel framework CLARE, which fuses data CLAssification and tag REcommendation into a coherent model. With experiments on three social media datasets, we demonstrate that the proposed framework CLARE achieves superior performance on both tasks compared to the state-of-the-art methods.

One particular challenge is to ground human language to robot internal representation of the physical world. Although copresent in a shared environment, humans and robots have mismatched capabilities in reasoning, perception, and action. A robot not only needs to incorporate collaborative effort from human partners to better connect human language to its own representation, but also needs to make extra collaborative effort to communicate its representation in language that humans can understand. This article gives a brief introduction to this research effort and discusses several collaborative approaches to grounding language to perception and action.

To enable situated human-robot dialogue, techniques to support grounded language communication are essential. One particular challenge is to ground human language to robot internal representation of the physical world. Although copresent in a shared environment, humans and robots have mismatched capabilities in reasoning, perception, and action. Their representations of the shared environment and joint tasks are significantly misaligned. Humans and robots will need to make extra effort to bridge the gap and strive for a common ground of the shared world. Only then, is the robot able to engage in language communication and joint tasks. Thus computational models for language grounding will need to take collaboration into consideration. A robot not only needs to incorporate collaborative effort from human partners to better connect human language to its own representation, but also needs to make extra collaborative effort to communicate its representation in language that humans can understand. To address these issues, the Language and Interaction Research group (LAIR) at Michigan State University has investigated multiple aspects of collaborative language grounding. This article gives a brief introduction to this research effort and discusses several collaborative approaches to grounding language to perception and action.

Several discriminative models with latent variables were also explored to learn better alignment models in a wetlab The Conference of the North American Chapter of the Association experiment domain (Naim et al. 2015). As alignment is for Computational Linguistics: Human Language often the first step in many problems involving language and Technology (NAACL HLT) is a premier conference reporting vision, these approaches and empirical results provide important outstanding research on human language technology.

Green security — protection of forests, fish and wildlife — is a critical problem in environmental sustainability. We focus on the problem  of  optimizing the defense of forests againstillegal logging, where often we are faced with the challenge of teaming up many different groups,  from national police to forest guards to NGOs, each with differing capabilities and costs. This paper introduces a new, yet fundamental problem: SimultaneousOptimization of Resource Teams and Tactics (SORT).  SORT contrasts with most previous game-theoretic research for green security — in particular based onsecurity games — that has solely focused on optimizing patrolling tactics, without consideration of team formation or coordination.  We develop new models and scalable algorithms to apply SORT towards illegal logging in large forest areas. We evaluate our methods on a variety of synthetic examples, as well as a real-world case study using data from our on-going collaboration in Madagascar .

To enable effective collaborations between humans and cognitive robots, it is important for robots to continuously acquire task knowledge from human partners. To address this issue, we are currently developing a framework that supports task learning through visual demonstration and natural language dialogue. One core component of this framework is the integration of language and vision that is driven by dialogue for task knowledge learning. This paper describes our on-going effort, particularly, grounded task learning through joint processing of video and dialogue using And-Or-Graphs (AOG).

While if kernels are not Kernel methods (Schölkopf and Smola 2002; Xu et al. 2009) low rank, Nyström approximations can usually lead to suboptimal have received a lot of attention in recent studies of machine performances. To alleviate the strong assumption in learning. These methods project data into high-dimensional the seeking of the approximation bounds, we take a more or even infinite-dimensional spaces via kernel mapping general assumption that the design matrix K ensuring the restricted functions. Despite the strong generalization ability induced isometric property (Koltchinskii 2011). In particular, by kernel methods, they usually suffer from the high computation the new assumption obeys the restricted eigenvalue condition complexity of calculating the kernel matrix (also (Koltchinskii 2011; Bickel, Ritov, and Tsybakov 2009), called Gram matrix). Although low-rank decomposition which has been shown to be more general than several techniques(e.g., Cholesky Decomposition (Fine and Scheinberg other similar assumptions used in sparsity literature (Candes 2002; Bach and Jordan 2005)), and truncating methods(e.g., and Tao 2007; Donoho, Elad, and Temlyakov 2006; Kernel Tapering (Shen, Xu, and Allebach 2014; Zhang and Huang 2008). Based on the restricted eigenvalue Furrer, Genton, and Nychka 2006)) can accelerate the calculation condition, we have provided error bounds for kernel approximation of the kernel matrix, they still need to compute the and recovery rate in sparse kernel regression.