arXiv subjects

Hang Li

Publications and source records attributed to Hang Li.

At least 199 records · Page 11Linked to original sources

arXiv2023

Features Disentangled Semantic Broadcast Communication Networks

Single-user semantic communications have attracted extensive research recently, but multi-user semantic broadcast communication (BC) is still in its infancy. In this paper, we propose a practical robust features-disentangled multi-user semantic BC framework, where the transmitter includes a feature selection module and each user has a feature completion module. Instead of broadcasting all extracted features, the semantic encoder extracts the disentangled semantic features, and then only the users' intended semantic features are selected for broadcasting, which can further improve the transmission efficiency. Within this framework, we further investigate two information-theoretic metrics, including the ultimate compression rate under both the distortion and perception constraints, and the achievable rate region of the semantic BC. Furthermore, to realize the proposed semantic BC framework, we design a lightweight robust semantic BC network by exploiting a supervised autoencoder (AE), which can controllably disentangle sematic features. Moreover, we design the first hardware proof-of-concept prototype of the semantic BC network, where the proposed semantic BC network can be implemented in real time. Simulations and experiments demonstrate that the proposed robust semantic BC network can significantly improve transmission efficiency.

eess.SP↗

arXiv2023

Task-oriented Explainable Semantic Communications

Semantic communications utilize the transceiver computing resources to alleviate scarce transmission resources, such as bandwidth and energy. Although the conventional deep learning (DL) based designs may achieve certain transmission efficiency, the uninterpretability issue of extracted features is the major challenge in the development of semantic communications. In this paper, we propose an explainable and robust semantic communication framework by incorporating the well-established bit-level communication system, which not only extracts and disentangles features into independent and semantically interpretable features, but also only selects task-relevant features for transmission, instead of all extracted features. Based on this framework, we derive the optimal input for rate-distortion-perception theory, and derive both lower and upper bounds on the semantic channel capacity. Furthermore, based on the $β$-variational autoencoder ($β$-VAE), we propose a practical explainable semantic communication system design, which simultaneously achieves semantic features selection and is robust against semantic channel noise. We further design a real-time wireless mobile semantic communication proof-of-concept prototype. Our simulations and experiments demonstrate that our proposed explainable semantic communications system can significantly improve transmission efficiency, and also verify the effectiveness of our proposed robust semantic transmission scheme.

eess.SP↗

arXiv2023

Learning to Counterfactually Explain Recommendations

Recommender system practitioners are facing increasing pressure to explain recommendations. We explore how to explain recommendations using counterfactual logic, i.e. "Had you not interacted with the following items, we would not recommend it." Compared to the traditional explanation logic, counterfactual explanations are easier to understand, more technically verifiable, and more informative in terms of giving users control over recommendations. The major challenge of generating such explanations is the computational cost because it requires repeatedly retraining the models to obtain the effect on a recommendation caused by the absence of user history. We propose a learning-based framework to generate counterfactual explanations. The key idea is to train a surrogate model to learn the effect of removing a subset of user history on the recommendation. To this end, we first artificially simulate the counterfactual outcomes on the recommendation after deleting subsets of history. Then we train a surrogate model to learn the mapping between a history deletion and the corresponding change of the recommendation caused by the deletion. Finally, to generate an explanation, we find the history subset predicted by the surrogate model that is most likely to remove the recommendation. Through offline experiments and online user studies, we show our method, compared to baselines, can generate explanations that are more counterfactually valid and more satisfactory considered by users.

cs.AI↗

arXiv2023

Kainate receptor modulation by NETO2

Glutamate-gated kainate receptors (KARs) are ubiquitous in the central nervous system of vertebrates, mediate synaptic transmission on post-synapse, and modulate transmitter release on pre-synapse. In the brain, the trafficking, gating kinetics, and pharmacology of KARs are tightly regulated by Neuropilin and tolloid-like proteins (Netos). Here we report cryo-EM structures of homo-tetrameric GluK2 in complex with Neto2 at inhibited and desensitized states, illustrating variable stoichiometry of GluK2-Neto2 complexes, with one or two Neto2 subunits associate with the GluK2. We find that Neto2 accesses only two broad faces of KARs, intermolecularly crosslinking the lower-lobe of ATDA/C, upper-lobe of LBDB/D, and lower-lobe of LBDA/C, illustrating how Neto2 regulates receptor-gating kinetics. The transmembrane helix of Neto2 is positioned proximal to the selectivity filter and competes with the amphiphilic H1-helix after M4 for interacting with an ICD formed by the M1-M2 linkers of the receptor, revealing how rectification is regulated by Neto2.

q-bio.BM↗

arXiv2023

Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive Attributes

Evaluating fairness can be challenging in practice because the sensitive attributes of data are often inaccessible due to privacy constraints. The go-to approach that the industry frequently adopts is using off-the-shelf proxy models to predict the missing sensitive attributes, e.g. Meta [Alao et al., 2021] and Twitter [Belli et al., 2022]. Despite its popularity, there are three important questions unanswered: (1) Is directly using proxies efficacious in measuring fairness? (2) If not, is it possible to accurately evaluate fairness using proxies only? (3) Given the ethical controversy over inferring user private information, is it possible to only use weak (i.e. inaccurate) proxies in order to protect privacy? Our theoretical analyses show that directly using proxy models can give a false sense of (un)fairness. Second, we develop an algorithm that is able to measure fairness (provably) accurately with only three properly identified proxies. Third, we show that our algorithm allows the use of only weak proxies (e.g. with only 68.85%accuracy on COMPAS), adding an extra layer of protection on user privacy. Experiments validate our theoretical analyses and show our algorithm can effectively measure and mitigate bias. Our results imply a set of practical guidelines for practitioners on how to use proxies properly. Code is available at github.com/UCSC-REAL/fair-eval.

cs.LG↗

arXiv2023

The Tensor Brain: A Unified Theory of Perception, Memory and Semantic Decoding

We present a unified computational theory of an agent's perception and memory. In our model, perception, episodic memory, and semantic memory are realized by different operational modes of the oscillating interactions between a symbolic index layer and a subsymbolic representation layer. The two layers form a bilayer tensor network (BTN). Although memory appears to be about the past, its main purpose is to support the agent in the present and the future. Recent episodic memory provides the agent with a sense of the here and now. Remote episodic memory retrieves relevant past experiences to provide information about possible future scenarios. This aids the agent in decision-making. "Future" episodic memory, based on expected future events, guides planning and action. Semantic memory retrieves specific information, which is not delivered by current perception, and defines priors for future observations. We argue that it is important for the agent to encode individual entities, not just classes and attributes. We demonstrate that a form of self-supervised learning can acquire new concepts and refine existing ones. We test our model on a standard benchmark data set, which we expanded to contain richer representations for attributes, classes, and individuals. Our key hypothesis is that obtaining a better understanding of perception and memory is a crucial prerequisite to comprehending human-level intelligence.

cs.AI↗

arXiv2023

Disentangled Representation for Diversified Recommendations

Accuracy and diversity have long been considered to be two conflicting goals for recommendations. We point out, however, that as the diversity is typically measured by certain pre-selected item attributes, e.g., category as the most popularly employed one, improved diversity can be achieved without sacrificing recommendation accuracy, as long as the diversification respects the user's preference about the pre-selected attributes. This calls for a fine-grained understanding of a user's preferences over items, where one needs to recognize the user's choice is driven by the quality of the item itself, or the pre-selected attributes of the item. In this work, we focus on diversity defined on item categories. We propose a general diversification framework agnostic to the choice of recommendation algorithms. Our solution disentangles the learnt user representation in the recommendation module into category-independent and category-dependent components to differentiate a user's preference over items from two orthogonal perspectives. Experimental results on three benchmark datasets and online A/B test demonstrate the effectiveness of our solution in improving both recommendation accuracy and diversity. In-depth analysis suggests that the improvement is due to our improved modeling of users' categorical preferences and refined ranking within item categories.

cs.IR↗

arXiv2023

A semi-discrete first-order low regularity exponential integrator for the "good" Boussinesq equation without loss of regularity

In this paper, we propose a semi-discrete first-order low regularity exponential-type integrator (LREI) for the ``good" Boussinesq equation. It is shown that the method is convergent linearly in the space $H^r$ for solutions belonging to $H^{r+p(r)}$ where $0\le p(r)\le 1$ is non-increasing with respect to $r$, which means less additional derivatives might be needed when the numerical solution is measured in a more regular space. Particularly, the LREI presents the first-order accuracy in $H^{r}$ with no assumptions of additional derivatives when $r>5/2$. This is the first time to propose a low regularity method which achieves the optimal first-order accuracy without loss of regularity for the GB equation. The convergence is confirmed by extensive numerical experiments.

math.NA↗

arXiv2022

AgAsk: An Agent to Help Answer Farmer's Questions From Scientific Documents

Decisions in agriculture are increasingly data-driven; however, valuable agricultural knowledge is often locked away in free-text reports, manuals and journal articles. Specialised search systems are needed that can mine agricultural information to provide relevant answers to users' questions. This paper presents AgAsk -- an agent able to answer natural language agriculture questions by mining scientific documents. We carefully survey and analyse farmers' information needs. On the basis of these needs we release an information retrieval test collection comprising real questions, a large collection of scientific documents split in passages, and ground truth relevance assessments indicating which passages are relevant to each question. We implement and evaluate a number of information retrieval models to answer farmers questions, including two state-of-the-art neural ranking models. We show that neural rankers are highly effective at matching passages to questions in this context. Finally, we propose a deployment architecture for AgAsk that includes a client based on the Telegram messaging platform and retrieval model deployed on commodity hardware. The test collection we provide is intended to stimulate more research in methods to match natural language to answers in scientific documents. While the retrieval models were evaluated in the agriculture domain, they are generalisable and of interest to others working on similar problems. The test collection is available at: \url{https://github.com/ielab/agvaluate}.

cs.IR↗

arXiv2022

Joint Beamforming and PD Orientation Design for Mobile Visible Light Communications

In this paper, we propose joint beamforming and photo-detector (PD) orientation (BO) optimization schemes for mobile visible light communication (VLC) with the orientation adjustable receiver (OAR). Since VLC is sensitive to line-of-sight propagation, we first establish the OAR model and the human body blockage model for mobile VLC user equipment (UE). To guarantee the quality of service (QoS) of mobile VLC, we jointly optimize BO with minimal UE the power consumption for both fixed and random UE orientation cases. For the fixed UE orientation case, since the {transmit} beamforming and the PD orientation are mutually coupled, the joint BO optimization problem is nonconvex and intractable. To address this challenge, we propose an alternating optimization algorithm to obtain the transmit beamforming and the PD orientation. For the random UE orientation case, we further propose a robust alternating BO optimization algorithm to ensure the worst-case QoS requirement of the mobile UE. Finally, the performance of joint BO optimization design schemes are evaluated for mobile VLC through numerical experiments.

eess.SP↗

arXiv2022

Simultaneously sorting vector vortex beams of 120 modes

Polarization (P), angular index (l), and radius index (p) are three independent degrees of freedom (DoFs) of vector vortex beams, which have been widely used in optical communications, quantum optics, information processing, etc. Although the sorting of one DoF can be achieved efficiently, it is still a great challenge to sort all these DoFs simultaneously in a compact and efficient way. Here, we propose a beam sorter to deal with all these three DoFs simultaneously by using a diffractive deep neural network (D$^2$NN) and experimentally demonstrated the robust sorting of 120 Laguerre-Gaussian (LG) modes using a compact D$^2$NN formed by one spatial light modulator and one mirror only. The proposed beam sorter demonstrates the great potential of D$^2$NN in optical field manipulation and will benefit the diverse applications of vector vortex beams.

physics.optics↗

arXiv2022

Counterfactually Evaluating Explanations in Recommender Systems

Modern recommender systems face an increasing need to explain their recommendations. Despite considerable progress in this area, evaluating the quality of explanations remains a significant challenge for researchers and practitioners. Prior work mainly conducts human study to evaluate explanation quality, which is usually expensive, time-consuming, and prone to human bias. In this paper, we propose an offline evaluation method that can be computed without human involvement. To evaluate an explanation, our method quantifies its counterfactual impact on the recommendation. To validate the effectiveness of our method, we carry out an online user study. We show that, compared to conventional methods, our method can produce evaluation scores more correlated with the real human judgments, and therefore can serve as a better proxy for human evaluation. In addition, we show that explanations with high evaluation scores are considered better by humans. Our findings highlight the promising direction of using the counterfactual approach as one possible way to evaluate recommendation explanations.

cs.AI↗

arXiv2022

A Neural-Symbolic Approach to Natural Language Understanding

Deep neural networks, empowered by pre-trained language models, have achieved remarkable results in natural language understanding (NLU) tasks. However, their performances can drastically deteriorate when logical reasoning is needed. This is because NLU in principle depends on not only analogical reasoning, which deep neural networks are good at, but also logical reasoning. According to the dual-process theory, analogical reasoning and logical reasoning are respectively carried out by System 1 and System 2 in the human brain. Inspired by the theory, we present a novel framework for NLU called Neural-Symbolic Processor (NSP), which performs analogical reasoning based on neural processing and logical reasoning based on both neural and symbolic processing. As a case study, we conduct experiments on two NLU tasks, question answering (QA) and natural language inference (NLI), when numerical reasoning (a type of logical reasoning) is necessary. The experimental results show that our method significantly outperforms state-of-the-art methods in both tasks.

cs.CL↗

arXiv2022

Solution of lepton $g-2$ anomalies with nonlocal QED

The explanation for lepton $g-2$ anomalies is provided with the nonlocal QED which is the simple extension of the standard model. This solution is based on the same gauge symmetry as QED without introducing any new particles and interactions. The correlation functions in the nonlocal strength tension and lepton-photon interaction make it possible to explain the discrepancies of both $Δa_μ$ and $Δa_e$. With the same approach, the discrepancy of anomalous magnetic moment of $τ$ lepton from standard model is estimated in the range $1.19\times10^{-5}$ to $3.21\times10^{-3}$ which is covered by the current experimental uncertainty.

hep-ph↗

arXiv2022

Optimal Probabilistic Constellation Shaping for Covert Communications

In this paper, we investigate the optimal probabilistic constellation shaping design for covert communication systems from a practical view. Different from conventional covert communications with equiprobable constellations modulation, we propose nonequiprobable constellations modulation schemes to further enhance the covert rate. Specifically, we derive covert rate expressions for practical discrete constellation inputs for the first time. Then, we study the covert rate maximization problem by jointly optimizing the constellation distribution and power allocation. In particular, an approximate gradient descent method is proposed for obtaining the optimal probabilistic constellation shaping. To strike a balance between the computational complexity and the transmission performance, we further develop a framework that maximizes a lower bound on the achievable rate where the optimal probabilistic constellation shaping problem can be solved efficiently using the Frank-Wolfe method. Extensive numerical results show that the optimized probabilistic constellation shaping strategies provide significant gains in the achievable covert rate over the state-of-the-art schemes.

cs.IT↗

arXiv2022

Optimal Power Allocation for Integrated Visible Light Positioning and Communication System with a Single LED-Lamp

In this paper, we investigate an integrated visible light positioning and communication (VLPC) system with a single LED-lamp. First, by leveraging the fact that the VLC channel model is a function of the receiver's location, we propose a system model that estimates the channel state information (CSI) based on the positioning information without transmitting pilot sequences. Second, we derive the Cramer-Rao lower bound (CRLB) on the positioning error variance and a lower bound on the achievable rate with on-off keying modulation. Third, based on the derived performance metrics, we optimize the power allocation to minimize the CRLB, while satisfying the rate outage probability constraint. To tackle this non-convex optimization problem, we apply the worst-case distribution of the Conditional Value-at-Risk (CVaR) and the block coordinate descent (BCD) methods to obtain the feasible solutions. Finally, the effects of critical system parameters, such as outage probability, rate threshold, total power threshold, are revealed by numerical results.

cs.IT↗

arXiv2022

Biologically Inspired Neural Path Finding

The human brain can be considered to be a graphical structure comprising of tens of billions of biological neurons connected by synapses. It has the remarkable ability to automatically re-route information flow through alternate paths in case some neurons are damaged. Moreover, the brain is capable of retaining information and applying it to similar but completely unseen scenarios. In this paper, we take inspiration from these attributes of the brain, to develop a computational framework to find the optimal low cost path between a source node and a destination node in a generalized graph. We show that our framework is capable of handling unseen graphs at test time. Moreover, it can find alternate optimal paths, when nodes are arbitrarily added or removed during inference, while maintaining a fixed prediction time. Code is available here: https://github.com/hangligit/pathfinding

cs.LG↗

arXiv2022

Forgetting Fast in Recommender Systems

Users of a recommender system may want part of their data being deleted, not only from the data repository but also from the underlying machine learning model, for privacy or utility reasons. Such right-to-be-forgotten requests could be fulfilled by simply retraining the recommendation model from scratch, but that would be too slow and too expensive in practice. In this paper, we investigate fast machine unlearning techniques for recommender systems that can remove the effect of a small amount of training data from the recommendation model without incurring the full cost of retraining. A natural idea to speed this process up is to fine-tune the current recommendation model on the remaining training data instead of starting from a random initialization. This warm-start strategy indeed works for neural recommendation models using standard 1st-order neural network optimizers (like AdamW). However, we have found that even greater acceleration could be achieved by employing 2nd-order (Newton or quasi-Newton) optimization methods instead. To overcome the prohibitively high computational cost of 2nd-order optimizers, we propose a new recommendation unlearning approach AltEraser which divides the optimization problem of unlearning into many small tractable sub-problems. Extensive experiments on three real-world recommendation datasets show promising results of AltEraser in terms of consistency (forgetting thoroughness), accuracy (recommendation effectiveness), and efficiency (unlearning speed). To our knowledge, this work represents the first attempt at fast approximate machine unlearning for state-of-the-art neural recommendation models.

cs.IR↗