We propose a cross-modal co-attention model for continuous emotion recognition using visual-audio-linguistic information. The model consists of four blocks. The visual, audio, and linguistic blocks are used to learn the spatial-temporal features of the multi-modal input. A co-attention block is designed to fuse the learned features with the multi-head co-attention mechanism. The visual encoding from the visual block is concatenated with the attention feature to emphasize the visual information. To make full use of the data and alleviate over-fitting, cross-validation is carried out on the training and validation set. The concordance correlation coefficient (CCC) centering is used to merge the results from each fold. The achieved CCC on the test set is $0.520$ for valence and $0.602$ for arousal, which significantly outperforms the baseline method with the corresponding CCC of 0.180 and 0.170 for valence and arousal, respectively. The code is available at https://github.com/sucv/ABAW3.
Datacenters execute large computational jobs, which are composed of smaller tasks. A job completes when all its tasks finish, so stragglers -- rare, yet extremely slow tasks -- are a major impediment to datacenter performance. Accurately predicting stragglers would enable proactive intervention, allowing datacenter operators to mitigate stragglers before they delay a job. While much prior work applies machine learning to predict computer system performance, these approaches rely on complete labels -- i.e., sufficient examples of all possible behaviors, including straggling and non-straggling -- or strong assumptions about the underlying latency distributions -- e.g., whether Gaussian or not. Within a running job, however, none of this information is available until stragglers have revealed themselves when they have already delayed the job. To predict stragglers accurately and early without labeled positive examples or assumptions on latency distributions, this paper presents NURD, a novel Negative-Unlabeled learning approach with Reweighting and Distribution-compensation that only trains on negative and unlabeled streaming data. The key idea is to train a predictor using finished tasks of non-stragglers to predict latency for unlabeled running tasks, and then reweight each unlabeled task's prediction based on a weighting function of its feature space. We evaluate NURD on two production traces from Google and Alibaba, and find that compared to the best baseline approach, NURD produces 2--11 percentage point increases in the F1 score in terms of prediction accuracy, and 4.7--8.8 percentage point improvements in job completion time.
We establish a high-dimensional statistical learning framework for individualized asset allocation. Our proposed methodology addresses continuous-action decision-making with a large number of characteristics. We develop a discretization approach to model the effect from continuous actions and allow the discretization level to be large and diverge with the number of observations. The value function of continuous-action is estimated using penalized regression with generalized penalties that are imposed on linear transformations of the model coefficients. We show that our estimators using generalized folded concave penalties enjoy desirable theoretical properties and allow for statistical inference of the optimal value associated with optimal decision-making. Empirically, the proposed framework is exercised with the Health and Retirement Study data in finding individualized optimal asset allocation. The results show that our individualized optimal strategy improves individual financial well-being and surpasses benchmark strategies.
Surrogates, models that mimic the behavior of programs, form the basis of a variety of development workflows. We study three surrogate-based design patterns, evaluating each in case studies on a large-scale CPU simulator. With surrogate compilation, programmers develop a surrogate that mimics the behavior of a program to deploy to end-users in place of the original program. Surrogate compilation accelerates the CPU simulator under study by $1.6\times$. With surrogate adaptation, programmers develop a surrogate of a program then retrain that surrogate on a different task. Surrogate adaptation decreases the simulator's error by up to $50\%$. With surrogate optimization, programmers develop a surrogate of a program, optimize input parameters of the surrogate, then plug the optimized input parameters back into the original program. Surrogate optimization finds simulation parameters that decrease the simulator's error by $5\%$ compared to the error induced by expert-set parameters. In this paper we formalize this taxonomy of surrogate-based design patterns. We further describe the programming methodology common to all three design patterns. Our work builds a foundation for the emerging class of workflows based on programming with surrogates of programs.
Multimodal classification is a core task in human-centric machine learning. We observe that information is highly complementary across modalities, thus unimodal information can be drastically sparsified prior to multimodal fusion without loss of accuracy. To this end, we present Sparse Fusion Transformers (SFT), a novel multimodal fusion method for transformers that performs comparably to existing state-of-the-art methods while having greatly reduced memory footprint and computation cost. Key to our idea is a sparse-pooling block that reduces unimodal token sets prior to cross-modality modeling. Evaluations are conducted on multiple multimodal benchmark datasets for a wide range of classification tasks. State-of-the-art performance is obtained on multiple benchmarks under similar experiment conditions, while reporting up to six-fold reduction in computational cost and memory requirements. Extensive ablation studies showcase our benefits of combining sparsification and multimodal learning over naive approaches. This paves the way for enabling multimodal learning on low-resource devices.
We propose an audio-visual spatial-temporal deep neural network with: (1) a visual block containing a pretrained 2D-CNN followed by a temporal convolutional network (TCN); (2) an aural block containing several parallel TCNs; and (3) a leader-follower attentive fusion block combining the audio-visual information. The TCN with large history coverage enables our model to exploit spatial-temporal information within a much larger window length (i.e., 300) than that from the baseline and state-of-the-art methods (i.e., 36 or 48). The fusion block emphasizes the visual modality while exploits the noisy aural modality using the inter-modality attention mechanism. To make full use of the data and alleviate over-fitting, cross-validation is carried out on the training and validation set. The concordance correlation coefficient (CCC) centering is used to merge the results from each fold. On the development set, the achieved CCC is 0.469 for valence and 0.649 for arousal, which significantly outperforms the baseline method with the corresponding CCC of 0.210 and 0.230 for valence and arousal, respectively. The code is available at https://github.com/sucv/ABAW2.
In this paper, we propose LGG, a neurologically inspired graph neural network, to learn local-global-graph representations from Electroencephalography (EEG) for a Brain-Computer Interface (BCI). A temporal convolutional layer with multi-scale 1D convolutional kernels and kernel-level attention fusion is proposed to learn the temporal dynamics of EEG. Inspired by neurological knowledge of cognitive processes in the brain, we propose local and global graph-filtering layers to learn the brain activities within and between different functional areas of the brain to model the complex relations among them during the cognitive processes. Under the robust nested cross-validation settings, the proposed method is evaluated on the publicly available dataset DEAP, and the classification performance is compared with state-of-the-art methods, such as FBFgMDM, FBTSC, Unsupervised learning, DeepConvNet, ShallowConvNet, EEGNet, and TSception. The results show that the proposed method outperforms all these state-of-the-art methods, and the improvements are statistically significant (p<0.05) in most cases. The source code can be found at: https://github.com/yi-ding-cs/LGG
In this paper, we propose TSception, a multi-scale convolutional neural network, to learn temporal dynamics and spatial asymmetry from affective electroencephalogram (EEG). TSception consists of dynamic temporal, asymmetric spatial, and high-level fusion Layers, which learn discriminative representations in the time and channel dimensions simultaneously. The dynamic temporal layer consists of multi-scale 1D convolutional kernels whose lengths are related to the sampling rate of the EEG signal, which learns its dynamic temporal and frequency representations. The asymmetric spatial layer takes advantage of the asymmetric neural activations underlying emotional responses, learning the discriminative global and hemisphere representations. The learned spatial representations will be fused by a high-level fusion layer. With robust nested cross-validation settings, the proposed method is evaluated on two publicly available datasets DEAP and AMIGOS. And the performance is compared with prior reported methods such as FBFgMDM, FBTSC, Unsupervised learning, DeepConvNet, ShallowConvNet, and EEGNet. The results indicate that the proposed method significantly (p<0.05) outperforms others in terms of classification accuracy. The proposed methods can be utilized in emotion regulation therapy for emotion recognition in the future. The source code can be found at: https://github.com/deepBrains/TSception-New