BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Hari Sundaram

Hari Sundaram appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Social and Information Networksphysics.soc-phMachine LearningInformation RetrievalArtificial Intelligencecs.CYData Structures and AlgorithmsDatabasesMultimedia

Catalog footprint

What is connected

11works
9topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

11 published item(s)

preprint2026arXiv

State Contamination in Memory-Augmented LLM Agents

LLM agents increasingly rely on persistent state, including transcripts, summaries, retrieved context, and memory buffers, to support long-horizon interaction. This makes safety depend not only on individual model outputs, but also on what an agent stores and later reuses. We study a failure mode we call memory laundering: toxic or adversarial context can be compressed into memory summaries that no longer appear toxic under standard detectors, while still preserving hostile framing or conflict structure that influences future generations. Using paired counterfactual multi-agent rollouts, we show that toxic-origin memory summaries can remain below common toxicity thresholds while nevertheless increasing downstream toxicity relative to matched neutral baselines. To measure this hidden influence, we introduce the sub-threshold propagation gap (SPG), which quantifies downstream behavioral differences conditioned on memory states that a deployed monitor would classify as safe. Our experiments show that toxicity propagates through distinct state channels: raw transcript reuse drives overt downstream toxicity, while compressed memory carries hidden sub-threshold influence. We further find that mitigation depends critically on intervention placement. Sanitizing toxic state before summarization substantially reduces the hidden propagation gap, whereas cleaning only the completed summary can leave laundered influence intact. These results suggest that safety in memory-augmented agents should be treated as a state-control problem over evolving context, with sanitization applied before unsafe information is compressed into persistent memory.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Beyond Localized Graph Neural Networks: An Attributed Motif Regularization Framework

We present InfoMotif, a new semi-supervised, motif-regularized, learning framework over graphs. We overcome two key limitations of message passing in popular graph neural networks (GNNs): localization (a k-layer GNN cannot utilize features outside the k-hop neighborhood of the labeled training nodes) and over-smoothed (structurally indistinguishable) representations. We propose the concept of attributed structural roles of nodes based on their occurrence in different network motifs, independent of network proximity. Two nodes share attributed structural roles if they participate in topologically similar motif instances over co-varying sets of attributes. Further, InfoMotif achieves architecture independence by regularizing the node representations of arbitrary GNNs via mutual information maximization. Our training curriculum dynamically prioritizes multiple motifs in the learning process without relying on distributional assumptions in the underlying graph or the learning task. We integrate three state-of-the-art GNNs in our framework, to show significant gains (3-10% accuracy) across six diverse, real-world datasets. We see stronger gains for nodes with sparse training labels and diverse attributes in local neighborhood structures.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Discovering Strategic Behaviors for Collaborative Content-Production in Social Networks

Some social networks provide explicit mechanisms to allocate social rewards such as reputation based on user activity, while the mechanism is more opaque in other networks. Nonetheless, there are always individuals who obtain greater rewards and reputation than their peers. An intuitive yet important question to ask is whether these successful users employ strategic behaviors to become influential. It might appear that the influencers have gamed the system. However, it remains difficult to conclude the rationality of their actions due to factors like the combinatorial strategy space, inability to determine payoffs, and resource limitations faced by individuals. The challenging nature of this question has drawn attention from both the theory and data mining communities. Therefore, in this paper, we are motivated to investigate if resource-limited individuals discover strategic behaviors associated with high payoffs when producing collaborative or interactive content in social networks. We propose a novel framework of Dynamic Dual Attention Networks or DDAN which models content production strategies of users through a generative process, under the influence of social interactions involved in the process. Extensive experimental results illustrate the effectiveness of our model in modeling user behavior. We make three strong empirical findings. Different strategies give rise to different social payoffs, the best performing individuals exhibit stability in their preference over the discovered strategies, which indicates the emergence of strategic behavior, and the stability of strategy preference is correlated with high payoffs.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

GroupIM: A Mutual Information Maximization Framework for Neural Group Recommendation

We study the problem of making item recommendations to ephemeral groups, which comprise users with limited or no historical activities together. Existing studies target persistent groups with substantial activity history, while ephemeral groups lack historical interactions. To overcome group interaction sparsity, we propose data-driven regularization strategies to exploit both the preference covariance amongst users who are in the same group, as well as the contextual relevance of users' individual preferences to each group. We make two contributions. First, we present a recommender architecture-agnostic framework GroupIM that can integrate arbitrary neural preference encoders and aggregators for ephemeral group recommendation. Second, we regularize the user-group latent space to overcome group interaction sparsity by: maximizing mutual information between representations of groups and group members; and dynamically prioritizing the preferences of highly informative members through contextual preference weighting. Our experimental results on several real-world datasets indicate significant performance improvements (31-62% relative NDCG@20) over state-of-the-art group recommendation techniques.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Transfer Learning via Contextual Invariants for One-to-Many Cross-Domain Recommendation

The rapid proliferation of new users and items on the social web has aggravated the gray-sheep user/long-tail item challenge in recommender systems. Historically, cross-domain co-clustering methods have successfully leveraged shared users and items across dense and sparse domains to improve inference quality. However, they rely on shared rating data and cannot scale to multiple sparse target domains (i.e., the one-to-many transfer setting). This, combined with the increasing adoption of neural recommender architectures, motivates us to develop scalable neural layer-transfer approaches for cross-domain learning. Our key intuition is to guide neural collaborative filtering with domain-invariant components shared across the dense and sparse domains, improving the user and item representations learned in the sparse domains. We leverage contextual invariances across domains to develop these shared modules, and demonstrate that with user-item interaction context, we can learn-to-learn informative representation spaces even with sparse interaction data. We show the effectiveness and scalability of our approach on two public datasets and a massive transaction dataset from Visa, a global payments technology company (19% Item Recall, 3x faster vs. training separate models for each domain). Our approach is applicable to both implicit and explicit feedback settings.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

It's just a matter of perspective(s): Crowd-Powered Consensus Organization of Corpora

We study the problem of organizing a collection of objects - images, videos - into clusters, using crowdsourcing. This problem is notoriously hard for computers to do automatically, and even with crowd workers, is challenging to orchestrate: (a) workers may cluster based on different latent hierarchies or perspectives; (b) workers may cluster at different granularities even when clustering using the same perspective; and (c) workers may only see a small portion of the objects when deciding how to cluster them (and therefore have limited understanding of the "big picture"). We develop cost-efficient, accurate algorithms for identifying the consensus organization (i.e., the organizing perspective most workers prefer to employ), and incorporate these algorithms into a cost-effective workflow for organizing a collection of objects, termed ORCHESTRA. We compare our algorithms with other algorithms for clustering, on a variety of real-world datasets, and demonstrate that ORCHESTRA organizes items better and at significantly lower costs.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Leveraging Social Foci for Information Seeking in Social Media

The rise of social media provides a great opportunity for people to reach out to their social connections to satisfy their information needs. However, generic social media platforms are not explicitly designed to assist information seeking of users. In this paper, we propose a novel framework to identify the social connections of a user able to satisfy his information needs. The information need of a social media user is subjective and personal, and we investigate the utility of his social context to identify people able to satisfy it. We present questions users post on Twitter as instances of information seeking activities in social media. We infer soft community memberships of the asker and his social connections by integrating network and content information. Drawing concepts from the social foci theory, we identify answerers who share communities with the asker w.r.t. the question. Our experiments demonstrate that the framework is effective in identifying answerers to social media questions.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Network Cartography: Seeing the Forest and the Trees

Real-world networks are often complex and large with millions of nodes, posing a great challenge for analysts to quickly see the big picture for more productive subsequent analysis. We aim at facilitating exploration of node-attributed networks by creating representations with conciseness, expressiveness, interpretability, and multi-resolution views. We develop such a representation as a {\it map} --- among the first to explore principled network cartography for general networks. In parallel with common maps, ours has landmarks, which aggregate nodes homogeneous in their traits and interactions with nodes elsewhere, and roads, which represent the interactions between the landmarks. We capture such homogeneity by the similar roles the nodes played. Next, to concretely model the landmarks, we propose a probabilistic generative model of networks with roles as latent factors. Furthermore, to enable interactive zooming, we formulate novel model-based constrained optimization. Then, we design efficient linear-time algorithms for the optimizations. Experiments using real-world and synthetic networks show that our method produces more expressive maps than existing methods, with up to 10 times improvement in network reconstruction quality. We also show that our method extracts landmarks with more homogeneous nodes, with up to 90\% improvement in the average attribute/link entropy among the nodes over each landmark. Sense-making of a real-world network using a map computed by our method qualitatively verify the effectiveness of our method.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

How Do We Find Early Adopters Who Will Guide a Resource Constrained Network Towards a Desired Distribution of Behaviors?

We identify influential early adopters that achieve a target behavior distribution for a resource constrained social network with multiple costly behaviors. This problem is important for applications ranging from collective behavior change to corporate viral marketing campaigns. In this paper, we propose a model of diffusion of multiple behaviors when individual participants have resource constraints. Individuals adopt the set of behaviors that maximize their utility subject to available resources. We show that the problem of influence maximization for multiple behaviors is NP-complete. Thus we propose heuristics, which are based on node degree and expected immediate adoption, to select early adopters. We evaluate the effectiveness under three metrics: unique number of participants, total number of active behaviors and network resource utilization. We also propose heuristics to distribute the behaviors amongst the early adopters to achieve a target distribution in the population. We test our approach on synthetic and real-world topologies with excellent results. Our heuristics produce 15-51\% increase in resource utilization over the naïve approach.

0 citations0 reviewsNo code linkedOpen access
preprint2012arXiv

Social Event Detection with Interaction Graph Modeling

This paper focuses on detecting social, physical-world events from photos posted on social media sites. The problem is important: cheap media capture devices have significantly increased the number of photos shared on these sites. The main contribution of this paper is to incorporate online social interaction features in the detection of physical events. We believe that online social interaction reflect important signals among the participants on the "social affinity" of two photos, thereby helping event detection. We compute social affinity via a random-walk on a social interaction graph to determine similarity between two photos on the graph. We train a support vector machine classifier to combine the social affinity between photos and photo-centric metadata including time, location, tags and description. Incremental clustering is then used to group photos to event clusters. We have very good results on two large scale real-world datasets: Upcoming and MediaEval. We show an improvement between 0.06-0.10 in F1 on these datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2010arXiv

"Birds of a Feather": Does User Homophily Impact Information Diffusion in Social Media?

This article investigates the impact of user homophily on the social process of information diffusion in online social media. Over several decades, social scientists have been interested in the idea that similarity breeds connection: precisely known as "homophily". Homophily has been extensively studied in the social sciences and refers to the idea that users in a social system tend to bond more with ones who are similar to them than to ones who are dissimilar. The key observation is that homophily structures the ego-networks of individuals and impacts their communication behavior. It is therefore likely to effect the mechanisms in which information propagates among them. To this effect, we investigate the interplay between homophily along diverse user attributes and the information diffusion process on social media. In our approach, we first extract diffusion characteristics---corresponding to the baseline social graph as well as graphs filtered on different user attributes (e.g. location, activity). Second, we propose a Dynamic Bayesian Network based framework to predict diffusion characteristics at a future time. Third, the impact of attribute homophily is quantified by the ability of the predicted characteristics in explaining actual diffusion, and external variables, including trends in search and news. Experimental results on a large Twitter dataset demonstrate that choice of the homophilous attribute can impact the prediction of information diffusion, given a specific metric and a topic. In most cases, attribute homophily is able to explain the actual diffusion and external trends by ~15-25% over cases when homophily is not considered.

0 citations0 reviewsNo code linkedOpen access