United States

A major challenge in scene graph classification is that the appearance of objects and relations can be significantly different from one image to another. Previous works have addressed this by relational reasoning over all objects in an image or incorporating prior knowledge into classification. Unlike previous works, we do not consider separate models for perception and prior knowledge. Instead, we take a multi-task learning approach by introducing schema representations and implementing the classification as an attention layer between image-based representations and the schemata. This allows for the prior knowledge to emerge and propagate within the perception model.Â By enforcing the model also to represent the prior, we achieve a strong inductive bias. We show that our model can accurately generate commonsense knowledge and that the iterative injection of this knowledge to scene representations, as a top-down mechanism, leads to significantly higher classification performance. Additionally, our model can be fine-tuned on external knowledge given as triples. When combined with self-supervised learning and with 1% of annotated images only, this gives more than 3% improvement in object classification, 26% in scene graph classification, and 36% in predicate prediction accuracy.

AAAI 2021

Classification by Attention: Scene Graph Classification with Prior Knowledge

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

AAAI 2022

technical paper

Human emotion decoding in affective brain-computer interfaces suffers a major setback due to the inter-subject variability of electroencephalography (EEG) signals. Existing approaches usually require amassing extensive EEG data of each new subject, which is prohibitively time-consuming along with poor user experience. To tackle this issue, we divide EEG representations into private components specific to each subject and shared emotional components that are universal to all subjects. According to this representation partition, we propose a plug-and-play domain adaptation method for dealing with the inter-subject variability. In the training phase, subject-invariant emotional representations and private components of source subjects are separately captured by a shared encoder and private encoders. Furthermore, we build one emotion classifier on the shared partition and subjects' individual classifiers on the combination of these two partitions. In the calibration phase, the model only requires few unlabeled EEG data from incoming target subjects to model their private components. Therefore, besides the shared emotion classifier, we have another pipeline to use the knowledge of source subjects through the similarity of private components. In the test phase, we integrate predictions of the shared emotion classifier with those of individual classifiers ensemble after modulation by similarity weights. Experimental results on the SEED dataset show that our model greatly shortens the calibration time within a minute while maintaining the recognition accuracy, all of which make emotion decoding more generalizable and practicable.

Plug-and-Play Domain Adaptation for Cross-Subject EEG-Based Emotion Recognition

Bipartite network inference is a ubiquitous problem across disciplines. One important example in the field molecular biology is gene regulatory network inference. Gene regulatory networks are an instrumental tool aiding in the discovery of the molecular mechanisms driving diverse diseases, including cancer. However, only noisy observations of the projections of these regulatory networks are typically assayed. In an effort to better estimate regulatory networks from their noisy projections, we formulate a non-convex but analytically tractable optimization problem called OTTER. This problem can be interpreted as relaxed graph matching between the two projections of the bipartite network. OTTER's solutions can be derived explicitly and inspire a spectral algorithm, for which we provide network recovery guarantees. We also provide an alternative approach based on gradient descent that is more robust to noise compared to the spectral algorithm. Interestingly, this gradient descent approach resembles the message passing equations of an established gene regulatory network inference method, PANDA.
Using three cancer-related data sets, we show that OTTER outperforms state-of-the-art inference methods in predicting transcription factor binding to gene regulatory regions. To encourage new graph matching applications to this problem, we have made all networks and validation data publicly available.

Gene Regulatory Network Inference as Relaxed Graph Matching

The paper develops a theory of power for delegable proxy voting systems. We define a power index able to measure the influence of both voters and delegators. Using this index, which we characterize axiomatically, we extend an earlier game-theoretic model by incorporating power-seeking behavior by agents. We analytically study the existence of pure strategy Nash equilibria in such a model. Finally, by means of simulations, we study the effect of several parameters on the emergence of power inequalities in the model.

Power in Liquid Democracy

We show generalisation error bounds for deep learning with two main improvements over the state of the art. (1) Our bounds have no explicit dependence on the number of classes except for logarithmic factors. This holds even when formulating the bounds in terms of the Frobenius-norm of the weight matrices, where previous bounds exhibit at least a square-root dependence on the number of classes.
(2) We adapt the classic Rademacher analysis of DNNs to incorporate weight sharing---a task of fundamental theoretical importance which was previously attempted only under very restrictive assumptions. In our results, each convolutional filter contributes only once to the bound, regardless of how many times it is applied. Further improvements exploiting pooling and sparse connections are provided.
The presented bounds scale as the norms of the parameter matrices, rather than the number of parameters. In particular, contrary to bounds based on parameter counting, they are asymptotically tight (up to log factors) when the weights approach initialisation, making them suitable as a basic ingredient in bounds sensitive to the optimisation procedure. We also show how to adapt the recent technique of loss function augmentation to replace spectral norms by empirical analogues whilst maintaining the advantages of our approach.

Norm-Based Generalisation Bounds for Deep Multi-Class Convolutional Neural Networks

Interest in physical therapy and individual exercises such as yoga/dance has increased alongside the well-being trend, and people globally enjoy such exercises at home/office via video streaming platforms. However, such exercises are hard to follow without expert guidance. Even if experts can help, it is almost impossible to give personalized feedback to every trainee remotely. Thus, automated pose correction systems are required more than ever, and we introduce a new captioning dataset named FixMyPose to address this need. We collect natural language descriptions of correcting a â€œcurrentâ€ pose to look like a â€œtargetâ€ pose. To support a multilingual setup, we collect descriptions in both English and Hindi. The collected descriptions have interesting linguistic properties such as egocentric relations to the environment objects, analogous references, etc., requiring an understanding of spatial relations and commonsense knowledge about postures. Further, to avoid ML biases, we maintain a balance across characters with diverse demographics, who perform a variety of movements in several interior environments (e.g., homes, offices). From our FixMyPose dataset, we introduce two tasks: the pose-correctional-captioning task and its reverse, the target-pose-retrieval task. During the correctional-captioning task, models must generate the descriptions of how to move from the current to the target pose image, whereas in the retrieval task, models should select the correct target pose given the initial pose and the correctional description. We present strong cross-attention baseline models (uni/multimodal, RL, multilingual) and also show that our baselines are competitive with other models when evaluated on other image-difference datasets. We also propose new task-specific metrics (object-match, body-part-match, direction-match) and conduct human evaluation for more reliable evaluation, and we demonstrate a large human-model performance gap suggesting room for promising future work. Finally, to verify the sim-to-real transfer of our FixMyPose dataset, we collect a set of real images and show promising performance on these images. Data and code are available: https://fixmypose-unc.github.io.

FixMyPose: Pose Correctional Captioning and Retrieval

Verifiable training has shown success in creating neural networks that are provably robust to a given amount of noise. However, despite only enforcing a single robustness criterion, its performance scales poorly with dataset complexity. On CIFAR10, a non-robust LeNet model has a 21.63% error rate, while a model created using verifiable training and a L-infinity robustness criterion of 8/255, has an error rate of 57.10%. Upon examination, we find that when labeling visually similar classes, the model's error rate is as high as 61.65%. Thus, we attribute the loss in performance to inter-class similarity. Classes that are similar (i.e., close in the feature space) increase the difficulty of learning a robust model. While it may be desirable to train a model to be robust for a large robustness region, pairwise class similarities limit the potential gains. Furthermore, consideration must be made regarding the relative cost of mistaking one class for another. In security or safety critical tasks, similar classes are likely to belong to the same group, and thus are equally sensitive.

In this work, we propose a new approach that utilizes inter-class similarity to improve the performance of verifiable training and create robust models with respect to multiple adversarial criteria. First, we cluster similar classes using agglomerate clustering and assign robustness criteria based on the degree of similarity between clusters.  Next, we propose two methods to apply our approach: (1) the Inter-Group Robustness Prioritization method, which uses a custom loss term to create a single model with multiple robustness guarantees and (2) the neural decision tree method, which trains multiple sub-classifiers with different robustness guarantees and combines them in a decision tree architecture. Our experiments on Fashion-MNIST and CIFAR10 demonstrate that by prioritizing the robustness between the most dissimilar groups, we improve clean performance by up to 9.63% and 30.89% respectively. Furthermore, on CIFAR100, our approach reduces the clean error rate by 26.32%.

Adaptive Verifiable Training Using Pairwise Class Similarity

Organizations that collect and sell data face increasing scrutiny for the discriminatory use of data. We propose a novel unsupervised approach to map data into a compressed binary representation independent of sensitive attributes. We show that in an information bottleneck framework,  a parsimonious representation should filter out information related to sensitive attributes if they are provided directly to the decoder. Empirical results show that the method achieves state-of-the-art accuracy-fairness trade-off  and that explicit control of the entropy of the representation bit stream allows the user to move smoothly and simultaneously along both rate-distortion and rate-fairness curves.

Fair Representations by Compression

We introduce a new (Ïµâ‚š, Î´â‚š)-differentially private algorithm for the k-means clustering problem. Given a dataset in Euclidean space, the k-means clustering problem requires one to find k points in that space such that the sum of squares of Euclidean distances between each data point and its closest respective point among the k returned is minimised. Although there exist privacy-preserving methods with good theoretical guarantees to solve this problem, in practice it is seen that it is the additive error which dictates the practical performance of these methods. By reducing the problem to a sequence of instances of maximum coverage on a grid, we are able to derive a new method that achieves lower additive error than previous works. For input datasets with cardinality n and diameter Î”, our algorithm has an O(Î”Â² (k logÂ² n  log(1/Î´â‚š)/Ïµâ‚š + k âˆš(d log(1/Î´â‚š))/Ïµâ‚š)) additive error whilst maintaining constant multiplicative error. We conclude with some experiments and find an improvement over previously implemented work for this problem.

Differentially Private k-Means via Exponential Mechanism and Max Cover

We study the complexity of determining a winning committee under the Chamberlin-Courant voting rule when voters' preferences are single-crossing on a line, or, more generally, on a tree. For the line, Skowron et al. (2015) describe an O(n^2mk) algorithm (where n, m, k are the number of voters, the number of candidates and the committee size, respectively); we show that a simple tweak improves the time complexity to O(nmk). We then improve this bound for k=Î©(log n) by reducing our problem to the k-link path problem for DAGs with concave Monge weights, obtaining a nm2^O(âˆš(log k log log n)) algorithm for the general case and a nearly linear algorithm for the Borda misrepresentation function. For trees, we point out an issue with the algorithm proposed by Clearwater, Puppe and Slinko (2015), and develop a O(nmk) algorithm for this case as well.

Proportional Representation under Single-Crossing Preferences Revisited

This paper introduces CloudLSTM, a new branch of recurrent neural models tailored to forecasting over data streams generated by geospatial point-cloud sources. We design a Dynamic Point-cloud Convolution (DConv) operator as the core component of CloudLSTMs, which performs convolution directly over point-clouds and extracts local spatial features from sets of neighboring points that surround different elements of the input. This operator maintains the permutation invariance of sequence-to-sequence learning frameworks, while representing neighboring correlations at each time step -- an important aspect in spatiotemporal predictive learning. The DConv operator resolves the grid-structural data requirements of existing spatiotemporal forecasting models and can be easily plugged into traditional LSTM architectures with sequence-to-sequence learning and attention mechanisms. We apply our proposed architecture to two representative, practical use cases that involve point-cloud streams, i.e. mobile service traffic forecasting and air quality indicator forecasting. Our results, obtained with real-world datasets collected in diverse scenarios for each use case, show that CloudLSTM delivers accurate long-term predictions, outperforming a variety of competitor neural network models.

Downloads

Next from AAAI 2021

Plug-and-Play Domain Adaptation for Cross-Subject EEG-Based Emotion Recognition

Similar lecture

Improving Scene Graph Classification by Exploiting Knowledge from Texts

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2021

Plug-and-Play Domain Adaptation for Cross-Subject EEG-Based Emotion Recognition

Similar lecture

Improving Scene Graph Classification by Exploiting Knowledge from Texts

Downloads