Search

We study a challenging problem of unsupervised discovery of object landmarks. Many recent methods rely on bottlenecks to generate 2D Gaussian heatmaps however, these are limited in generating informed heatmaps while training, presumably due to the lack of effective structural cues. Also, it is assumed that all predicted landmarks are semantically relevant despite having no ground truth supervision. In the current work, we introduce a consistency-guided bottleneck in an image reconstruction-based pipeline that leverages landmark consistency, a measure of compatibility score with the pseudo-ground truth to generate adaptive heatmaps. We propose obtaining pseudo-supervision via forming landmark correspondence across images. The consistency then modulates the uncertainty of the discovered landmarks in the generation of adaptive heatmaps which rank consistent landmarks above their noisy counterparts, providing effective structural information for improved robustness. Evaluations on five diverse datasets including MAFL, AFLW, LS3D, Cats, and Shoes demonstrate excellent performance of the proposed approach compared to the existing state-of-the-art methods. Our code is publicly available at https://github.com/MamonaAwan/CGB_ULD., Comment: Accepted ORAL at BMVC 2023 ; Code: https://github.com/MamonaAwan/CGB_ULD

Joint source and channel coding (JSCC) has attracted increasing attention due to its robustness and high efficiency. However, JSCC is vulnerable to privacy leakage due to the high relevance between the source image and channel input. In this paper, we propose a disentangled information bottleneck guided privacy-protective JSCC (DIB-PPJSCC) for image transmission, which aims at protecting private information as well as achieving superior communication performance at the legitimate receiver. In particular, we propose a DIB objective to disentangle private and public information. The goal is to compress the private information in the public subcodewords, preserve the private information in the private subcodewords and improve the reconstruction quality simultaneously. In order to optimize JSCC neural networks using the DIB objective, we derive a differentiable estimation of the DIB objective based on the variational approximation and the density-ratio trick. Additionally, we design a password-based privacy-protective (PP) algorithm which can be jointly optimized with JSCC neural networks to encrypt the private subcodewords. Specifically, we employ a private information encryptor to encrypt the private subcodewords before transmission, and a corresponding decryptor to recover the private information at the legitimate receiver. A loss function for jointly training the encryptor, decryptor and JSCC decoder is derived based on the maximum entropy principle, which aims at maximizing the eavesdropping uncertainty as well as improving the reconstruction quality. Experimental results show that DIB-PPJSCC can reduce the eavesdropping accuracy on private information up to $15\%$ and reduce $10\%$ inference time compared to existing privacy-protective JSCC and traditional separate methods.

Markov processes are widely used mathematical models for describing dynamic systems in various fields. However, accurately simulating large-scale systems at long time scales is computationally expensive due to the short time steps required for accurate integration. In this paper, we introduce an inference process that maps complex systems into a simplified representational space and models large jumps in time. To achieve this, we propose Time-lagged Information Bottleneck (T-IB), a principled objective rooted in information theory, which aims to capture relevant temporal features while discarding high-frequency information to simplify the simulation task and minimize the inference error. Our experiments demonstrate that T-IB learns information-optimal representations for accurately modeling the statistical properties and dynamics of the original process at a selected time lag, outperforming existing time-lagged dimensionality reduction methods., Comment: 10 pages, 15 figures, Accepted ICLR 2024

A central challenge for cognitive science is to explain how abstract concepts are acquired from limited experience. This has often been framed in terms of a dichotomy between connectionist and symbolic cognitive models. Here, we highlight a recently emerging line of work that suggests a novel reconciliation of these approaches, by exploiting an inductive bias that we term the relational bottleneck. In that approach, neural networks are constrained via their architecture to focus on relations between perceptual inputs, rather than the attributes of individual inputs. We review a family of models that employ this approach to induce abstractions in a data-efficient manner, emphasizing their potential as candidate models for the acquisition of abstract concepts in the human mind and brain.

Controlling the relaxation dynamics of excitons is key to improving the efficiencies of semiconductor--based applications. Confined semiconductor nanocrystals (NCs) offer additional handles to control the properties of excitons, for example, by changing their size or shape, resulting in a mismatch between excitonic gaps and phonon frequencies. This has led to the hypothesis of a significant slowing--down of exciton relaxation in strongly confined NCs, but in practice due to increasing exciton--phonon coupling and rapid multiphonon relaxation channels, the exciton relaxation depends only weakly on the size or shape. Here, we focus on elucidating the nonradiative relaxation of excitons in NCs placed in an optical cavity. We find that multiphonon emission of carrier governs the decay resulting in a polariton--induced phonon bottleneck with relaxation timescales that are slower by orders of magnitude compared to the cavity--free case, while the photon fraction plays a secondary role.

Split learning is a privacy-preserving distributed learning paradigm in which an ML model (e.g., a neural network) is split into two parts (i.e., an encoder and a decoder). The encoder shares so-called latent representation, rather than raw data, for model training. In mobile-edge computing, network functions (such as traffic forecasting) can be trained via split learning where an encoder resides in a user equipment (UE) and a decoder resides in the edge network. Based on the data processing inequality and the information bottleneck (IB) theory, we present a new framework and training mechanism to enable a dynamic balancing of the transmission resource consumption with the informativeness of the shared latent representations, which directly impacts the predictive performance. The proposed training mechanism offers an encoder-decoder neural network architecture featuring multiple modes of complexity-relevance tradeoffs, enabling tunable performance. The adaptability can accommodate varying real-time network conditions and application requirements, potentially reducing operational expenditure and enhancing network agility. As a proof of concept, we apply the training mechanism to a millimeter-wave (mmWave)-enabled throughput prediction problem. We also offer new insights and highlight some challenges related to recurrent neural networks from the perspective of the IB theory. Interestingly, we find a compression phenomenon across the temporal domain of the sequential model, in addition to the compression phase that occurs with the number of training epochs., Comment: Accepted to Proc. IEEE Globecom 2023

Visible-Infrared person re-identification (VI-ReID) is an important and challenging task in intelligent video surveillance. Existing methods mainly focus on learning a shared feature space to reduce the modality discrepancy between visible and infrared modalities, which still leave two problems underexplored: information redundancy and modality complementarity. To this end, properly eliminating the identity-irrelevant information as well as making up for the modality-specific information are critical and remains a challenging endeavor. To tackle the above problems, we present a novel mutual information and modality consensus network, namely CMInfoNet, to extract modality-invariant identity features with the most representative information and reduce the redundancies. The key insight of our method is to find an optimal representation to capture more identity-relevant information and compress the irrelevant parts by optimizing a mutual information bottleneck trade-off. Besides, we propose an automatically search strategy to find the most prominent parts that identify the pedestrians. To eliminate the cross- and intra-modality variations, we also devise a modality consensus module to align the visible and infrared modalities for task-specific guidance. Moreover, the global-local feature representations can also be acquired for key parts discrimination. Experimental results on four benchmarks, i.e., SYSU-MM01, RegDB, Occluded-DukeMTMC, Occluded-REID, Partial-REID and Partial\_iLIDS dataset, have demonstrated the effectiveness of CMInfoNet.

Recognizing target objects using an event-based camera draws more and more attention in recent years. Existing works usually represent the event streams into point-cloud, voxel, image, etc, and learn the feature representations using various deep neural networks. Their final results may be limited by the following factors: monotonous modal expressions and the design of the network structure. To address the aforementioned challenges, this paper proposes a novel dual-stream framework for event representation, extraction, and fusion. This framework simultaneously models two common representations: event images and event voxels. By utilizing Transformer and Structured Graph Neural Network (GNN) architectures, spatial information and three-dimensional stereo information can be learned separately. Additionally, a bottleneck Transformer is introduced to facilitate the fusion of the dual-stream information. Extensive experiments demonstrate that our proposed framework achieves state-of-the-art performance on two widely used event-based classification datasets. The source code of this work is available at: \url{https://github.com/Event-AHU/EFV_event_classification}, Comment: Accepted by PRCV-2023

Interpretability is a crucial factor in building reliable models for various medical applications. Concept Bottleneck Models (CBMs) enable interpretable image classification by utilizing human-understandable concepts as intermediate targets. Unlike conventional methods that require extensive human labor to construct the concept set, recent works leveraging Large Language Models (LLMs) for generating concepts made automatic concept generation possible. However, those methods do not consider whether a concept is visually relevant or not, which is an important factor in computing meaningful concept scores. Therefore, we propose a visual activation score that measures whether the concept contains visual cues or not, which can be easily computed with unlabeled image data. Computed visual activation scores are then used to filter out the less visible concepts, thus resulting in a final concept set with visually meaningful concepts. Our experimental results show that adopting the proposed visual activation score for concept filtering consistently boosts performance compared to the baseline. Moreover, qualitative analyses also validate that visually relevant concepts are successfully selected with the visual activation score., Comment: Accepted to MedAGI Workshop at MICCAI 2023 (Oral Presentation)

Keyphrase extraction (KPE) is an important task in Natural Language Processing for many scenarios, which aims to extract keyphrases that are present in a given document. Many existing supervised methods treat KPE as sequential labeling, span-level classification, or generative tasks. However, these methods lack the ability to utilize keyphrase information, which may result in biased results. In this study, we propose Diff-KPE, which leverages the supervised Variational Information Bottleneck (VIB) to guide the text diffusion process for generating enhanced keyphrase representations. Diff-KPE first generates the desired keyphrase embeddings conditioned on the entire document and then injects the generated keyphrase embeddings into each phrase representation. A ranking network and VIB are then optimized together with rank loss and classification loss, respectively. This design of Diff-KPE allows us to rank each candidate phrase by utilizing both the information of keyphrases and the document. Experiments show that Diff-KPE outperforms existing KPE methods on a large open domain keyphrase extraction benchmark, OpenKP, and a scientific domain dataset, KP20K., Comment: 10 pages, 2 figures, accepted to LREC-COLING 2024

Artistic style transfer aims to transfer the style of an artwork to a photograph while maintaining its original overall content. Many prior works focus on designing various transfer modules to transfer the style statistics to the content image. Although effective, ignoring the clear disentanglement of the content features and the style features from the first beginning, they have difficulty in balancing between content preservation and style transferring. To tackle this problem, we propose a novel information disentanglement method, named InfoStyler, to capture the minimal sufficient information for both content and style representations from the pre-trained encoding network. InfoStyler formulates the disentanglement representation learning as an information compression problem by eliminating style statistics from the content image and removing the content structure from the style image. Besides, to further facilitate disentanglement learning, a cross-domain Information Bottleneck (IB) learning strategy is proposed by reconstructing the content and style domains. Extensive experiments demonstrate that our InfoStyler can synthesize high-quality stylized images while balancing content structure preservation and style pattern richness., Comment: Accepted by TCSVT 2023

The practice of code reuse is crucial in software development for a faster and more efficient development lifecycle. In reality, however, code reuse practices lack proper control, resulting in issues such as vulnerability propagation and intellectual property infringements. Assembly clone search, a critical shift-right defence mechanism, has been effective in identifying vulnerable code resulting from reuse in released executables. Recent studies on assembly clone search demonstrate a trend towards using machine learning-based methods to match assembly code variants produced by different toolchains. However, these methods are limited to what they learn from a small number of toolchain variants used in training, rendering them inapplicable to unseen architectures and their corresponding compilation toolchain variants. This paper presents the first study on the problem of assembly clone search with unseen architectures and libraries. We propose incorporating human common knowledge through large-scale pre-trained natural language models, in the form of transfer learning, into current learning-based approaches for assembly clone search. Transfer learning can aid in addressing the limitations of the existing approaches, as it can bring in broader knowledge from human experts in assembly code. We further address the sequence limit issue by proposing a reinforcement learning agent to remove unnecessary and redundant tokens. Coupled with a new Variational Information Bottleneck learning strategy, the proposed system minimizes the reliance on potential indicators of architectures and optimization settings, for a better generalization of unseen architectures. We simulate the unseen architecture clone search scenarios and the experimental results show the effectiveness of the proposed approach against the state-of-the-art solutions., Comment: 13 pages and 4 figures. This work has been submitted to the IEEE for possible publication

The cost of information processing in physical systems calls for a trade-off between performance and energetic expenditure. Here we formulate and study a computation-dissipation bottleneck in mesoscopic systems used as input-output devices. Using both real datasets and synthetic tasks, we show how non-equilibrium leads to enhanced performance. Our framework sheds light on a crucial compromise between information compression, input-output computation and dynamic irreversibility induced by non-reciprocal interactions., Comment: 12 pages, 5 figures

Driven by the need for more efficient and seamless integration of physical models and data, physics-informed neural networks (PINNs) have seen a surge of interest in recent years. However, ensuring the reliability of their convergence and accuracy remains a challenge. In this work, we propose an efficient, gradient-less weighting scheme for PINNs, that accelerates the convergence of dynamic or static systems. This simple yet effective attention mechanism is a function of the evolving cumulative residuals and aims to make the optimizer aware of problematic regions at no extra computational cost or adversarial learning. We illustrate that this general method consistently achieves a relative $L^{2}$ error of the order of $10^{-5}$ using standard optimizers on typical benchmark cases of the literature. Furthermore, by investigating the evolution of weights during training, we identify two distinct learning phases reminiscent of the fitting and diffusion phases proposed by the information bottleneck (IB) theory. Subsequent gradient analysis supports this hypothesis by aligning the transition from high to low signal-to-noise ratio (SNR) with the transition from fitting to diffusion regimes of the adopted weights. This novel correlation between PINNs and IB theory could open future possibilities for understanding the underlying mechanisms behind the training and stability of PINNs and, more broadly, of neural operators.

Graph Neural Networks (GNNs) have achieved great success in modeling graph-structured data. However, recent works show that GNNs are vulnerable to adversarial attacks which can fool the GNN model to make desired predictions of the attacker. In addition, training data of GNNs can be leaked under membership inference attacks. This largely hinders the adoption of GNNs in high-stake domains such as e-commerce, finance and bioinformatics. Though investigations have been made in conducting robust predictions and protecting membership privacy, they generally fail to simultaneously consider the robustness and membership privacy. Therefore, in this work, we study a novel problem of developing robust and membership privacy-preserving GNNs. Our analysis shows that Information Bottleneck (IB) can help filter out noisy information and regularize the predictions on labeled samples, which can benefit robustness and membership privacy. However, structural noises and lack of labels in node classification challenge the deployment of IB on graph-structured data. To mitigate these issues, we propose a novel graph information bottleneck framework that can alleviate structural noises with neighbor bottleneck. Pseudo labels are also incorporated in the optimization to minimize the gap between the predictions on the labeled set and unlabeled set for membership privacy. Extensive experiments on real-world datasets demonstrate that our method can give robust predictions and simultaneously preserve membership privacy.

Persistence diagrams (PDs) are used as signatures of point cloud data. Two clouds of points can be compared using the bottleneck distance d_B between their PDs. A potential drawback of this pipeline is that point clouds sampled from topologically similar manifolds can have arbitrarily large d_B when there is a large scaling between them. This situation is typical in dimension reduction frameworks. We define, and study properties of, a new scale-invariant distance between PDs termed normalized bottleneck distance, d_N. In defining d_N, we develop a broader framework called metric decomposition for comparing finite metric spaces of equal cardinality with a bijection. We utilize metric decomposition to prove a stability result for d_N by deriving an explicit bound on the distortion of the bijective map. We then study two popular dimension reduction techniques, Johnson-Lindenstrauss (JL) projections and metric multidimensional scaling (mMDS), and a third class of general biLipschitz mappings. We provide new bounds on how well these dimension reduction techniques preserve homology with respect to d_N. For a JL map f that transforms input X to f(X), we show that d_N(dgm(X),dgm(f(X))) < e, where dgm(X) is the Vietoris-Rips PD of X, and pairwise distances are preserved by f up to the tolerance 0 < \epsilon < 1. For mMDS, we present new bounds for d_B and d_N between PDs of X and its projection in terms of the eigenvalues of the covariance matrix. And for k-biLipschitz maps, we show that d_N is bounded by the product of (k^2-1)/k and the ratio of diameters of X and f(X). Finally, we use computational experiments to demonstrate the increased effectiveness of using the normalized bottleneck distance for clustering sets of point clouds sampled from different shapes., Comment: Added computational experiments; published in La Matematica

We introduce a novel nonlinear model, Sparse Adaptive Bottleneck Centroid-Encoder (SABCE), for determining the features that discriminate between two or more classes. The algorithm aims to extract discriminatory features in groups while reconstructing the class centroids in the ambient space and simultaneously use additional penalty terms in the bottleneck layer to decrease within-class scatter and increase the separation of different class centroids. The model has a sparsity-promoting layer (SPL) with a one-to-one connection to the input layer. Along with the primary objective, we minimize the $l_{2,1}$-norm of the sparse layer, which filters out unnecessary features from input data. During training, we update class centroids by taking the Hadamard product of the centroids and weights of the sparse layer, thus ignoring the irrelevant features from the target. Therefore the proposed method learns to reconstruct the critical components of class centroids rather than the whole centroids. The algorithm is applied to various real-world data sets, including high-dimensional biological, image, speech, and accelerometer sensor data. We compared our method to different state-of-the-art feature selection techniques, including supervised Concrete Autoencoders (SCAE), Feature Selection Networks (FsNet), Stochastic Gates (STG), and LassoNet. We empirically showed that SABCE features often produced better classification accuracy than other methods on the sequester test sets, setting new state-of-the-art results., Comment: A novel nonlinear feature selection technique with new state of the art result. 22 pages (including references), 13 figures. The article is in review

In this project we attempt to make slot-based models with an image reconstruction objective competitive with those that use a feature reconstruction objective on real world datasets. We propose a loss-based approach to constricting the bottleneck of slot-based models, allowing larger-capacity encoder networks to be used with Slot Attention without producing degenerate stripe-shaped masks. We find that our proposed method offers an improvement over the baseline Slot Attention model but does not reach the performance of \dinosaur on the COCO2017 dataset. Throughout this project, we confirm the superiority of a feature reconstruction objective over an image reconstruction objective and explore the role of the architectural bottleneck in slot-based models., Comment: 14 pages, 10 figures

Interpretable models are designed to make decisions in a human-interpretable manner. Representatively, Concept Bottleneck Models (CBM) follow a two-step process of concept prediction and class prediction based on the predicted concepts. CBM provides explanations with high-level concepts derived from concept predictions; thus, reliable concept predictions are important for trustworthiness. In this study, we address the ambiguity issue that can harm reliability. While the existence of a concept can often be ambiguous in the data, CBM predicts concepts deterministically without considering this ambiguity. To provide a reliable interpretation against this ambiguity, we propose Probabilistic Concept Bottleneck Models (ProbCBM). By leveraging probabilistic concept embeddings, ProbCBM models uncertainty in concept prediction and provides explanations based on the concept and its corresponding uncertainty. This uncertainty enhances the reliability of the explanations. Furthermore, as class uncertainty is derived from concept uncertainty in ProbCBM, we can explain class uncertainty by means of concept uncertainty. Code is publicly available at https://github.com/ejkim47/prob-cbm., Comment: International Conference on Machine Learning (ICML) 2023

Numerous deep learning algorithms have been inspired by and understood via the notion of information bottleneck, where unnecessary information is (often implicitly) minimized while task-relevant information is maximized. However, a rigorous argument for justifying why it is desirable to control information bottlenecks has been elusive. In this paper, we provide the first rigorous learning theory for justifying the benefit of information bottleneck in deep learning by mathematically relating information bottleneck to generalization errors. Our theory proves that controlling information bottleneck is one way to control generalization errors in deep learning, although it is not the only or necessary way. We investigate the merit of our new mathematical findings with experiments across a range of architectures and learning settings. In many cases, generalization errors are shown to correlate with the degree of information bottleneck: i.e., the amount of the unnecessary information at hidden layers. This paper provides a theoretical foundation for current and future methods through the lens of information bottleneck. Our new generalization bounds scale with the degree of information bottleneck, unlike the previous bounds that scale with the number of parameters, VC dimension, Rademacher complexity, stability or robustness. Our code is publicly available at: https://github.com/xu-ji/information-bottleneck, Comment: Accepted at ICML 2023. Code is available at https://github.com/xu-ji/information-bottleneck

Previous work has shown that DNNs with large depth $L$ and $L_{2}$-regularization are biased towards learning low-dimensional representations of the inputs, which can be interpreted as minimizing a notion of rank $R^{(0)}(f)$ of the learned function $f$, conjectured to be the Bottleneck rank. We compute finite depth corrections to this result, revealing a measure $R^{(1)}$ of regularity which bounds the pseudo-determinant of the Jacobian $\left|Jf(x)\right|_{+}$ and is subadditive under composition and addition. This formalizes a balance between learning low-dimensional representations and minimizing complexity/irregularity in the feature maps, allowing the network to learn the `right' inner dimension. Finally, we prove the conjectured bottleneck structure in the learned features as $L\to\infty$: for large depths, almost all hidden representations are approximately $R^{(0)}(f)$-dimensional, and almost all weight matrices $W_{\ell}$ have $R^{(0)}(f)$ singular values close to 1 while the others are $O(L^{-\frac{1}{2}})$. Interestingly, the use of large learning rates is required to guarantee an order $O(L)$ NTK which in turns guarantees infinite depth convergence of the representations of almost all layers.

Reinforcement Learning (RL) has recently achieved remarkable success in robotic control. However, most works in RL operate in simulated environments where privileged knowledge (e.g., dynamics, surroundings, terrains) is readily available. Conversely, in real-world scenarios, robot agents usually rely solely on local states (e.g., proprioceptive feedback of robot joints) to select actions, leading to a significant sim-to-real gap. Existing methods address this gap by either gradually reducing the reliance on privileged knowledge or performing a two-stage policy imitation. However, we argue that these methods are limited in their ability to fully leverage the available privileged knowledge, resulting in suboptimal performance. In this paper, we formulate the sim-to-real gap as an information bottleneck problem and therefore propose a novel privileged knowledge distillation method called the Historical Information Bottleneck (HIB). In particular, HIB learns a privileged knowledge representation from historical trajectories by capturing the underlying changeable dynamic information. Theoretical analysis shows that the learned privileged knowledge representation helps reduce the value discrepancy between the oracle and learned policies. Empirical experiments on both simulated and real-world tasks demonstrate that HIB yields improved generalizability compared to previous methods. Videos of real-world experiments are available at https://sites.google.com/view/history-ib ., Comment: Accepted by CoRL 2024

Video multimodal fusion aims to integrate multimodal signals in videos, such as visual, audio and text, to make a complementary prediction with multiple modalities contents. However, unlike other image-text multimodal tasks, video has longer multimodal sequences with more redundancy and noise in both visual and audio modalities. Prior denoising methods like forget gate are coarse in the granularity of noise filtering. They often suppress the redundant and noisy information at the risk of losing critical information. Therefore, we propose a denoising bottleneck fusion (DBF) model for fine-grained video multimodal fusion. On the one hand, we employ a bottleneck mechanism to filter out noise and redundancy with a restrained receptive field. On the other hand, we use a mutual information maximization module to regulate the filter-out module to preserve key information within different modalities. Our DBF model achieves significant improvement over current state-of-the-art baselines on multiple benchmarks covering multimodal sentiment analysis and multimodal summarization tasks. It proves that our model can effectively capture salient features from noisy and redundant video, audio, and text inputs. The code for this paper is publicly available at https://github.com/WSXRHFG/DBF., Comment: Accept at ACL2023

This paper considers the distributed information bottleneck (D-IB) problem for a primitive Gaussian diamond channel with two relays and MIMO Rayleigh fading. The channel state is an independent and identically distributed (i.i.d.) process known at the relays but unknown to the destination. The relays are oblivious, i.e., they are unaware of the codebook and treat the transmitted signal as a random process with known statistics. The bottleneck constraints prevent the relays to communicate the channel state information (CSI) perfectly to the destination. To evaluate the bottleneck rate, we provide an upper bound by assuming that the destination node knows the CSI and the relays can cooperate with each other, and also two achievable schemes with simple symbol-by-symbol relay processing and compression. Numerical results show that the lower bounds obtained by the proposed achievable schemes can come close to the upper bound on a wide range of relevant system parameters., Comment: arXiv admin note: text overlap with arXiv:2206.14453

Early detection of Alzheimer's Disease (AD) and its prodromal state, Mild Cognitive Impairment (MCI), is crucial for providing suitable treatment and preventing the disease from progressing. It can also aid researchers and clinicians to identify early biomarkers and minister new treatments that have been a subject of extensive research. The application of deep learning techniques on structural Magnetic Resonance Imaging (MRI) has shown promising results in diagnosing the disease. In this research, we intend to introduce a novel approach of using an ensemble of the self-attention-based Bottleneck Transformers with a sharpness aware minimizer for early detection of Alzheimer's Disease. The proposed approach has been tested on the widely accepted ADNI dataset and evaluated using accuracy, precision, recall, F1 score, and ROC-AUC score as the performance metrics.

This paper studies the multimodal named entity recognition (MNER) and multimodal relation extraction (MRE), which are important for multimedia social platform analysis. The core of MNER and MRE lies in incorporating evident visual information to enhance textual semantics, where two issues inherently demand investigations. The first issue is modality-noise, where the task-irrelevant information in each modality may be noises misleading the task prediction. The second issue is modality-gap, where representations from different modalities are inconsistent, preventing from building the semantic alignment between the text and image. To address these issues, we propose a novel method for MNER and MRE by Multi-Modal representation learning with Information Bottleneck (MMIB). For the first issue, a refinement-regularizer probes the information-bottleneck principle to balance the predictive evidence and noisy information, yielding expressive representations for prediction. For the second issue, an alignment-regularizer is proposed, where a mutual information-based item works in a contrastive manner to regularize the consistent text-image representations. To our best knowledge, we are the first to explore variational IB estimation for MNER and MRE. Experiments show that MMIB achieves the state-of-the-art performances on three public benchmarks.

In this paper, a PDE-ODE model with discontinuity in the flux as well as a flux constraint is analyzed. A modified Riemann solution is proposed and the existence of a weak solution to the Cauchy problem is rigorously investigated using the wavefront tracking scheme., Comment: 51 pages, 29 Figures

We study the long- and short-term effects of telecommuting (TLC), staggered work hours (SWH), and their combined scheme on peak-period congestion and location patterns. In order to enable a unified comparison of the schemes' long- and short-term effects, we develop a novel equilibrium analysis approach that consistently synthesizes the long-term equilibrium (location and percentage of telecommuting choice) and short-term equilibrium (preferred arrival time and departure time choice). By exploiting their special mathematical structures similar to optimal transport problems, we derive the closed-form solution to the long- and short-term equilibrium while explicitly considering their interaction. These closed-form solutions elucidate the discrepancies between the effects of each scheme and uncover a paradoxical finding: the introduction of SWH, in conjunction with TLC, may increase the total commuting costs compared to the scenario with only TLC, without yielding any improvement in worker utility., Comment: 38pages, 11 figures

Most modern computing tasks have digital electronic input and output data. Due to these constraints imposed by real-world use cases of computer systems, any analog computing accelerator, whether analog electronic or optical, must perform an analog-to-digital conversion on its input data and a subsequent digital-to-analog conversion on its output data. The energy and latency costs incurred by data conversion place performance limits on analog computing accelerators. To avoid this overhead, analog hardware must replace the full functionality of traditional digital electronic computer hardware. This is not currently possible for optical computing accelerators due to limitations in gain, input-output isolation, and information storage in optical hardware. This article presents a case study that profiles 27 benchmarks for an analog optical Fourier transform and convolution accelerator which we designed and built. The case study shows that an ideal optical Fourier transform and convolution accelerator can produce an average speedup of 9.4 times and a median speedup of 1.9 times for the set of benchmarks. The optical Fourier transform and convolution accelerator only produces significant speedup for pure Fourier transform (45.3 times) and convolution (159.4 times) applications., Comment: Accepted to the First Workshop on Machine Learning with New Compute Paradigms at NeurIPS 2023 (MLNPCP 2023)

As oxygen is essential for respiration and metabolism for multicellular organisms on Earth, its presence may be crucial for the development of a complex biosphere on other planets. And because life itself, through photosynthesis, contributed to creating our oxygen-rich atmosphere, oxygen has long been considered as a possible biosignature. Here we consider the relationship between atmospheric oxygen and the development of technology. We argue that only planets with substantial oxygen partial pressure ($p_{\rm O_2}$) will be capable of developing advanced technospheres and hence technosignatures that we can detect. But open-air combustion (needed, for example, for metallurgy), is possible only in Earth-like atmospheres when $p_{\rm O_2}\ge 18\%$. This limit is higher than the one needed to sustain a complex biosphere and multicellular organisms. We further review other possible planetary atmospheric compositions and conclude that oxygen is the most likely candidate for the evolution of technological species. Thus, the presence of $p_{\rm O_2}\ge 18\%$ in exoplanet atmospheres may represent a contextual prior required for the planning and interpretation of technosignature searches., Comment: 13 pages, 2 figures. Updated to match version published in Nature Astronomy (2023)

Speech recognition systems are a key intermediary in voice-driven human-computer interaction. Although speech recognition works well for pristine monologic audio, real-life use cases in open-ended interactive settings still present many challenges. We argue that timing is mission-critical for dialogue systems, and evaluate 5 major commercial ASR systems for their conversational and multilingual support. We find that word error rates for natural conversational data in 6 languages remain abysmal, and that overlap remains a key challenge (study 1). This impacts especially the recognition of conversational words (study 2), and in turn has dire consequences for downstream intent recognition (study 3). Our findings help to evaluate the current state of conversational ASR, contribute towards multidimensional error analysis and evaluation, and identify phenomena that need most attention on the way to build robust interactive speech technologies.

Conditional coding is a new video coding paradigm enabled by neural-network-based compression. It can be shown that conditional coding is in theory better than the traditional residual coding, which is widely used in video compression standards like HEVC or VVC. However, on closer inspection, it becomes clear that conditional coders can suffer from information bottlenecks in the prediction path, i.e., that due to the data processing inequality not all information from the prediction signal can be passed to the reconstructed signal, thereby impairing the coder performance. In this paper we propose the conditional residual coding concept, which we derive from information theoretical properties of the conditional coder. This coder significantly reduces the influence of bottlenecks, while maintaining the theoretical performance of the conditional coder. We provide a theoretical analysis of the coding paradigm and demonstrate the performance of the conditional residual coder in a practical example. We show that conditional residual coders alleviate the disadvantages of conditional coders while being able to maintain their advantages over residual coders. In the spectrum of residual and conditional coding, we can therefore consider them as ``the best from both worlds''., Comment: 12 pages, 8 figures Accepted for Publication in TCSVT

We train a generative language model on the randomized local measurement data collected from Schr\"odinger's cat quantum state. We demonstrate that the classical reality emerges in the language model due to the information bottleneck: although our training data contains the full quantum information about Schr\"odinger's cat, a weak language model can only learn to capture the classical reality of the cat from the data. We identify the quantum-classical boundary in terms of both the size of the quantum system and the information processing power of the classical intelligent agent, which indicates that a stronger agent can realize more quantum nature in the environmental noise surrounding the quantum system. Our approach opens up a new avenue for using the big data generated on noisy intermediate-scale quantum (NISQ) devices to train generative models for representation learning of quantum operators, which might be a step toward our ultimate goal of creating an artificial intelligence quantum physicist., Comment: 17 pages, 9 figures

In this research, we deal with the problem of visual question answering (VQA) in remote sensing. While remotely sensed images contain information significant for the task of identification and object detection, they pose a great challenge in their processing because of high dimensionality, volume and redundancy. Furthermore, processing image information jointly with language features adds additional constraints, such as mapping the corresponding image and language features. To handle this problem, we propose a cross attention based approach combined with information maximization. The CNN-LSTM based cross-attention highlights the information in the image and language modalities and establishes a connection between the two, while information maximization learns a low dimensional bottleneck layer, that has all the relevant information required to carry out the VQA task. We evaluate our method on two VQA remote sensing datasets of different resolutions. For the high resolution dataset, we achieve an overall accuracy of 79.11% and 73.87% for the two test sets while for the low resolution dataset, we achieve an overall accuracy of 85.98%.

Deep hashing has shown to be a complexity-efficient solution for the Approximate Nearest Neighbor search problem in high dimensional space. Many methods usually build the loss function from pairwise or triplet data points to capture the local similarity structure. Other existing methods construct the similarity graph and consider all points simultaneously. Auto-encoding Twin-bottleneck Hashing is one such method that dynamically builds the graph. Specifically, each input data is encoded into a binary code and a continuous variable, or the so-called twin bottlenecks. The similarity graph is then computed from these binary codes, which get updated consistently during the training. In this work, we generalize the original model into a supervised deep hashing network by incorporating the label information. In addition, we examine the differences of codes structure between these two networks and consider the class imbalance problem especially in multi-labeled datasets. Experiments on three datasets yield statistically significant improvement against the original model. Results are also comparable and competitive to other supervised methods.

We propose a novel scheme called advanced dual-chirped optical parametric amplification (DC-OPA) that employs two kinds of nonlinear crystals (BiB$_3$O$_6$ and MgO-doped lithium niobate) to overcome the bottleneck of pulse energy scalability for single-cycle mid-infrared (MIR) laser pulses. In experiments, the advanced DC-OPA scheme achieved carrier-to-envelope phase-stable MIR laser pulses for a bandwidth of over one octave (1.4-3.1 $\mu$m) with an output pulse energy of 53 mJ. The pulse duration was compressed to 8.58 fs, which corresponds to 1.05 cycles with a central wavelength of 2.44 $\mu$m and peak power of 6 TW. To our knowledge, the obtained values for the pulse energy and peak power are the highest achieved for optical parametric amplification of single-cycle MIR laser pulses. Thanks to the energy scalability of the advanced DC-OPA scheme, it is potentially applicable to multi-TW sub-cycle laser pulses., Comment: 18 pages, 6 figures

Performant vision-language (VL) models like CLIP represent captions using a single vector. How much information about language is lost in this bottleneck? We first curate CompPrompts, a set of increasingly compositional image captions that VL models should be able to capture (e.g., single object, to object+property, to multiple interacting objects). Then, we train text-only recovery probes that aim to reconstruct captions from single-vector text representations produced by several VL models. This approach does not require images, allowing us to test on a broader range of scenes compared to prior work. We find that: 1) CLIP's text encoder falls short on more compositional inputs, including object relationships, attribute-object association, counting, and negations; 2) some text encoders work significantly better than others; and 3) text-only recovery performance predicts multi-modal matching performance on ControlledImCaps: a new evaluation benchmark we collect and release consisting of fine-grained compositional images and captions. Specifically, our results suggest text-only recoverability is a necessary (but not sufficient) condition for modeling compositional factors in contrastive VL models. We release our datasets and code., Comment: EMNLP 2023

The prevalence of Transformer-based pre-trained language models (PLMs) has led to their wide adoption for various natural language processing tasks. However, their excessive overhead leads to large latency and computational costs. The statically compression methods allocate fixed computation to different samples, resulting in redundant computation. The dynamic token pruning method selectively shortens the sequences but are unable to change the model size and hardly achieve the speedups as static pruning. In this paper, we propose a model accelaration approaches for large language models that incorporates dynamic token downsampling and static pruning, optimized by the information bottleneck loss. Our model, Infor-Coef, achieves an 18x FLOPs speedup with an accuracy degradation of less than 8\% compared to BERT. This work provides a promising approach to compress and accelerate transformer-based models for NLP tasks.

Task-oriented communication is an emerging paradigm for next-generation communication networks, which extracts and transmits task-relevant information, instead of raw data, for downstream applications. Most existing deep learning (DL)-based task-oriented communication systems adopt a closed-world scenario, assuming either the same data distribution for training and testing, or the system could have access to a large out-of-distribution (OoD) dataset for retraining. However, in practical open-world scenarios, task-oriented communication systems need to handle unknown OoD data. Under such circumstances, the powerful approximation ability of learning methods may force the task-oriented communication systems to overfit the training data (i.e., in-distribution data) and provide overconfident judgments when encountering OoD data. Based on the information bottleneck (IB) framework, we propose a class conditional IB (CCIB) approach to address this problem in this paper, supported by information-theoretical insights. The idea is to extract distinguishable features from in-distribution data while keeping their compactness and informativeness. This is achieved by imposing the class conditional latent prior distribution and enforcing the latent of different classes to be far away from each other. Simulation results shall demonstrate that the proposed approach detects OoD data more efficiently than the baselines and state-of-the-art approaches, without compromising the rate-distortion tradeoff., Comment: code available in github, accepted by IEEE GLOBECOM2023

Neural collapse describes the geometry of activation in the final layer of a deep neural network when it is trained beyond performance plateaus. Open questions include whether neural collapse leads to better generalization and, if so, why and how training beyond the plateau helps. We model neural collapse as an information bottleneck (IB) problem in order to investigate whether such a compact representation exists and discover its connection to generalization. We demonstrate that neural collapse leads to good generalization specifically when it approaches an optimal IB solution of the classification problem. Recent research has shown that two deep neural networks independently trained with the same contrastive loss objective are linearly identifiable, meaning that the resulting representations are equivalent up to a matrix transformation. We leverage linear identifiability to approximate an analytical solution of the IB problem. This approximation demonstrates that when class means exhibit $K$-simplex Equiangular Tight Frame (ETF) behavior (e.g., $K$=10 for CIFAR10 and $K$=100 for CIFAR100), they coincide with the critical phase transitions of the corresponding IB problem. The performance plateau occurs once the optimal solution for the IB problem includes all of these phase transitions. We also show that the resulting $K$-simplex ETF can be packed into a $K$-dimensional Gaussian distribution using supervised contrastive learning with a ResNet50 backbone. This geometry suggests that the $K$-simplex ETF learned by supervised contrastive learning approximates the optimal features for source coding. Hence, there is a direct correspondence between optimal IB solutions and generalization in contrastive learning.