Distributed training of Deep Learning (DL) models on resource-constrained devices has gained significant interest. Training data-driven DL models collaboratively using federated learning (FL) and split learning (SL) have become the most popular ways to do this task. We aim to optimize these techniques by reducing device computation during parallel model training and reducing high-communication costs due to the frequent exchange of models, data, and gradients. This article proposes efficient SL (ESL), a novel approach addressing these challenges through three key ideas: 1) a key-value store for caching and sharing intermediate activations across clients, significantly reducing redundant computations and communication during the training phase; 2) customization of state-of-the-art neural networks for SL context; and 3) personalized training allowing clients to learn individual models tailored to their specific data distributions. Existing communication-efficient FL/SL methods trade accuracy to reduce communication. In contrast, ESL achieves significant communication reduction while maintaining high accuracy. Extensive experimentation on real-world federated benchmarks for image classification and 3-D segmentation demonstrates significant improvements over baseline FL techniques: ESL achieves a reduction in computation by$1623 \times $for image classification and$23.9 \times $for 3-D segmentation on resource-constrained devices. Additionally, it reduces communication traffic, during training, between clients and the server by$3.92 \times $for image classification and$1.3 \times $for 3-D segmentation while improving average accuracy by 35% and 31%, respectively. Furthermore, when compared to the baseline SL approaches, ESL reduces communication traffic during training by$100 \times $and improves accuracy by an average of 34.8%.

Several distributed frameworks have been developed to scale Graph Neural Networks (GNNs) on billion-size graphs. On several benchmarks, we observe that the graph partitions generated by these frameworks have heterogeneous data distributions and class imbalance, affecting convergence, and resulting in lower performance than centralized implementations. We holistically address these challenges and develop techniques that reduce training time and improve accuracy. We develop an Edge-Weighted partitioning technique to improve the micro average F1 score (accuracy) by minimizing the total entropy. Furthermore, we add an asynchronous personalization phase that adapts each compute-host’s model to its local data distribution. We design a class-balanced sampler that considerably speeds up convergence. We implemented our algorithms on the DistDGL framework and observed that our training techniques scale much better than the existing training approach. We achieved a (2-3x) speedup in training time and 4% improvement on average in micro-F1 scores on 5 large graph benchmarks compared to the standard baselines.

We examine the utility of implicit user behavioral signals captured using low-cost, off-the-shelf devices for anonymous gender and emotion recognition. A user study designed to examine male and female sensitivity to facial emotions confirms that females recognize (especially negative) emotions quicker and more accurately than men, mirroring prior findings. Implicit viewer responses in the form of EEG brain signals and eye movements are then examined for existence of (a) emotion and gender-specific patterns from event-related potentials (ERPs) and fixation distributions and (b) emotion and gender discriminability. Experiments reveal that (i) Gender and emotion-specific differences are observable from ERPs, (ii) multiple similarities exist between explicit responses gathered from users and their implicit behavioral signals, and (iii) Significantly above-chance (≈70%) gender recognition is achievable on comparing emotion-specific EEG responses– gender differences are encoded best for anger and disgust. Also, fairly modest valence (positive vs negative emotion) recognition is achieved with EEG and eye-based features.

Neural correlates corresponding to a specific cognitive tasks has been made possible with techniques like functional magnetic resonance imaging. The increasing number of neuroimaging studies has made meta-analysis methods popular for useful inferencing across multiple studies. The easy availability of neuroinformatic tools has also resulted in increasing the number of meta-analysis studies. We compare different meta-analysis approaches using hand-curated database (Brainmap) and automated database (neurosynth) using the case study of reward-related studies. We combine meta-analysis with atlas-based approaches to quantitatively compare different meta-analysis approaches. Based on our results, we propose further integration of different meta-analytic approaches with automated data mining methods for neuroimaging.